{"data":[{"id":"jev-latest","name":"jev-latest","created":1792634400,"description":"The latest iteration of TypeSafe's System One Model: Jev","context_length":64000,"architecture":{"modality":"text->decisions","input_modalities":["text"],"output_modalities":["decisions"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.2420000000000005e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0027148800000000002,"max_completion_cost":0.0,"max_cost":0.0027148800000000002},"sats_pricing":{"prompt":0.000053225393606930096,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.4064251908435264,"max_completion_cost":0.0,"max_cost":3.4064251908435264},"per_request_limits":null,"top_provider":{"context_length":64000,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"typesafe","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"jev-preview","name":"jev-preview","created":1792008840,"description":"Preview the next version of Jev before it gets promoted to jev-latest. Most of the time this is the same as jev-latest","context_length":64000,"architecture":{"modality":"text->decisions","input_modalities":["text"],"output_modalities":["decisions"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.2420000000000005e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0027148800000000002,"max_completion_cost":0.0,"max_cost":0.0027148800000000002},"sats_pricing":{"prompt":0.000053225393606930096,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.4064251908435264,"max_completion_cost":0.0,"max_cost":3.4064251908435264},"per_request_limits":null,"top_provider":{"context_length":64000,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"typesafe","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"jev-1.13.0","name":"jev-1.13.0","created":0,"description":"TypeSafe System One model jev-1.13.0","context_length":64000,"architecture":{"modality":"text->decisions","input_modalities":["text"],"output_modalities":["decisions"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.2420000000000005e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0027148800000000002,"max_completion_cost":0.0,"max_cost":0.0027148800000000002},"sats_pricing":{"prompt":0.000053225393606930096,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.4064251908435264,"max_completion_cost":0.0,"max_cost":3.4064251908435264},"per_request_limits":null,"top_provider":{"context_length":64000,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"typesafe","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-4-argon","name":"Gemini 4 Argon","created":1791849600,"description":"Gemini 4 Argon is Google's frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":2.7500000000000004,"max_completion_cost":0.9011200000000001,"max_cost":3.4708960000000006},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.017252455494938448,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0,"max_prompt_cost":3450.4910989876894,"max_completion_cost":1130.656923316286,"max_cost":4355.016637640718},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-3-6-flash","name":"Gemini 3.6 Flash","created":1783555200,"description":"Gemini 3.6 Flash, the successor to Gemini 3.5 Flash, is a high speed, high value thinking model with 1M context, designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.03125e-6,"completion":5.15625e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.03125e-7,"input_cache_write":0.0,"max_prompt_cost":1.03125,"max_completion_cost":0.33792,"max_cost":1.301586},"sats_pricing":{"prompt":0.0012939341621203834,"completion":0.006469670810601917,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00012939341621203833,"input_cache_write":0.0,"max_prompt_cost":1293.9341621203832,"max_completion_cost":423.9963462436072,"max_cost":1633.131239115269},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-3-7-flash","name":"Gemini 3.7 Flash","created":1786665600,"description":"Gemini 3.7 Flash, the successor to Gemini 3.6 Flash, is built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.03125e-6,"completion":5.15625e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.03125e-7,"input_cache_write":0.0,"max_prompt_cost":1.03125,"max_completion_cost":0.33792,"max_cost":1.301586},"sats_pricing":{"prompt":0.0012939341621203834,"completion":0.006469670810601917,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00012939341621203833,"input_cache_write":0.0,"max_prompt_cost":1293.9341621203832,"max_completion_cost":423.9963462436072,"max_cost":1633.131239115269},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","created":1788307200,"description":"Gemini 3.8 Flash, the successor to Gemini 3.7 Flash, is built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.03125e-6,"completion":5.15625e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.03125e-7,"input_cache_write":0.0,"max_prompt_cost":1.03125,"max_completion_cost":0.33792,"max_cost":1.301586},"sats_pricing":{"prompt":0.0012939341621203834,"completion":0.006469670810601917,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00012939341621203833,"input_cache_write":0.0,"max_prompt_cost":1293.9341621203832,"max_completion_cost":423.9963462436072,"max_cost":1633.131239115269},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-3-5-flash-lite","name":"Gemini 3.5 Flash-Lite","created":1783555200,"description":"Gemini 3.5 Flash-Lite is the fastest, most cost-efficient Gemini 3.5 model with 1M context, ideal for everyday questions, summarization, and lightweight coding tasks.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":3.4375000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.41250000000000003,"max_completion_cost":0.22528000000000004,"max_cost":0.6107464},"sats_pricing":{"prompt":0.0005175736648481533,"completion":0.004313113873734612,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000051757366484815334,"input_cache_write":0.0,"max_prompt_cost":517.5736648481534,"max_completion_cost":282.6642308290715,"max_cost":766.3181879777362},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"z-ai-glm-5-3","name":"GLM 5.3","created":1787011200,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":6.0500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.575e-7,"input_cache_write":0.0,"max_prompt_cost":1.9250000000000003,"max_completion_cost":0.7929856000000001,"max_cost":2.465672},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.007591080417772916,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00044856384286839955,"input_cache_write":0.0,"max_prompt_cost":2415.3437692913826,"max_completion_cost":994.9780925183317,"max_cost":3093.7379232811536},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"z-ai-glm-5-3-flash","name":"GLM 5.3 Flash","created":1787270400,"description":"GLM-5.3 Flash is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with visual context.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.0720896,"max_cost":0.22347776},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":90.45255386530287,"max_cost":280.4029169824389},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"zai-org-glm-5-2","name":"GLM 5.2","created":1781568000,"description":"GLM-5.2, the successor to GLM-5.1, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports a longer context window than GLM-5.1 for processing extensive text and detailed analysis with fast inference speed.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.54e-6,"completion":4.84e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.8600000000000005e-7,"input_cache_write":0.0,"max_prompt_cost":1.54,"max_completion_cost":0.63438848,"max_cost":1.9725376},"sats_pricing":{"prompt":0.0019322750154331058,"completion":0.0060728643342183326,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00035885107429471967,"input_cache_write":0.0,"max_prompt_cost":1932.2750154331056,"max_completion_cost":795.9824740146653,"max_cost":2474.9903386249225},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"zai-org-glm-5-1","name":"GLM 5.1","created":1775520000,"description":"GLM-5.1, the successor to GLM-5, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis with fast inference speed.","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.6940000000000002e-6,"completion":5.324000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.146e-7,"input_cache_write":0.0,"max_prompt_cost":0.33880000000000005,"max_completion_cost":0.4259200000000001,"max_cost":0.6292000000000001},"sats_pricing":{"prompt":0.0021255025169764166,"completion":0.006680150767640167,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003947361817241916,"input_cache_write":0.0,"max_prompt_cost":425.1005033952833,"max_completion_cost":534.4120614112134,"max_cost":789.4723634483832},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":80000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"zai-org-glm-5","name":"GLM 5","created":1770768000,"description":"GLM-5, the successor to GLM-4.7, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis.","context_length":198000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":3.5200000000000006e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000004e-7,"input_cache_write":0.0,"max_prompt_cost":0.21780000000000002,"max_completion_cost":0.11264000000000002,"max_cost":0.29524000000000006},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.004416628606704242,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":273.278895039825,"max_completion_cost":141.33211541453576,"max_cost":370.44472438731833},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":32000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"z-ai-glm-5-turbo","name":"GLM 5 Turbo","created":1773532800,"description":"GLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows.","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.64e-7,"input_cache_write":0.0,"max_prompt_cost":0.264,"max_completion_cost":0.1441792,"max_cost":0.36492544000000005},"sats_pricing":{"prompt":0.0016562357275140907,"completion":0.005520785758380302,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003312471455028181,"input_cache_write":0.0,"max_prompt_cost":331.2471455028181,"max_completion_cost":180.90510773060575,"max_cost":457.8807209142422},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"z-ai-glm-5v-turbo","name":"GLM 5V Turbo","created":1775001600,"description":"GLM-5V-Turbo is Z.ai's first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks with image and text inputs.","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.18022400000000002,"max_cost":0.45615680000000003},"sats_pricing":{"prompt":0.0020702946593926133,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00041405893187852267,"input_cache_write":0.0,"max_prompt_cost":414.0589318785227,"max_completion_cost":226.1313846632572,"max_cost":572.3509011428027},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"olafangensan-glm-4.7-flash-heretic","name":"GLM 4.7 Flash Heretic","created":1770163200,"description":"GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":7.700000000000001e-8,"completion":4.400000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.850000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.015400000000000002,"max_completion_cost":0.010560000000000002,"max_cost":0.024112000000000005},"sats_pricing":{"prompt":0.0000966137507716553,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004830687538582765,"input_cache_write":0.0,"max_prompt_cost":19.32275015433106,"max_completion_cost":13.249885820112727,"max_cost":30.25390595592406},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":24000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"zai-org-glm-4.6","name":"GLM 4.6","created":1711929600,"description":"GLM-4.6 is a large language model developed by Z.ai, featuring strong reasoning capabilities and support for multiple languages. Supports a large context window for processing extensive text and detailed analysis.","context_length":198000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.7300000000000007e-7,"completion":1.925e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.800000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.09365400000000002,"max_completion_cost":0.0315392,"max_cost":0.11744356800000001},"sats_pricing":{"prompt":0.0005934844690258825,"completion":0.0024153437692913822,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00011041571516760605,"input_cache_write":0.0,"max_prompt_cost":117.50992486712474,"max_completion_cost":39.57299231607001,"max_cost":147.3592676426747},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"zai-org-glm-4.7","name":"GLM 4.7","created":1766534400,"description":"GLM-4.7, the successor to GLM-4.6, is a large language model developed by Z.ai, featuring strong reasoning capabilities and support for multiple languages. Supports a large context window for processing extensive text and detailed analysis.","context_length":198000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":2.9150000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.21e-7,"input_cache_write":0.0,"max_prompt_cost":0.11979000000000001,"max_completion_cost":0.04775936000000001,"max_cost":0.15763704},"sats_pricing":{"prompt":0.0007591080417772916,"completion":0.0036575205649269507,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001518216083554583,"input_cache_write":0.0,"max_prompt_cost":150.30339227190373,"max_completion_cost":59.92481693576316,"max_cost":197.79098305118774},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"venice-uncensored-1-2","name":"Venice Uncensored 1.2","created":1775001600,"description":"Venice Uncensored 1.2 is designed for maximum creative freedom and authentic interaction. Built for open-ended exploration, roleplay, and unfiltered dialogue with improved capabilities over 1.1.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.028160000000000004,"max_completion_cost":0.00811008,"max_cost":0.034467840000000007},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.001242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":35.33302885363394,"max_completion_cost":10.175912309846574,"max_cost":43.24762731684794},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"venice-uncensored-role-play","name":"Venice Role Play Uncensored","created":1771545600,"description":"Optimized for creative roleplay scenarios with maximum freedom. Designed for immersive storytelling, character interactions, and open-ended creative writing.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0704,"max_completion_cost":0.0090112,"max_cost":0.0771584},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":88.33257213408484,"max_completion_cost":11.30656923316286,"max_cost":96.81249905895697},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-3-8-2-4t-a95b","name":"Qwen 3.8 2.4T","created":1786492800,"description":"Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.4375000000000004e-7,"input_cache_write":0.0,"max_prompt_cost":0.7208960000000001,"max_completion_cost":0.540672,"max_cost":1.081344},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00043131138737346114,"input_cache_write":0.0,"max_prompt_cost":904.5255386530288,"max_completion_cost":678.3941539897716,"max_cost":1356.788307979543},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-3-8-max","name":"Qwen 3.8 Max","created":1784678400,"description":"Qwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent performance. It accepts both text and vision-language input (images and video), operates in thinking mode only, and supports a 1M-token context window.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.4375000000000004e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.081344,"max_cost":3.470896},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00043131138737346114,"input_cache_write":0.004313113873734612,"max_prompt_cost":3450.4910989876894,"max_completion_cost":1356.788307979543,"max_cost":4355.016637640718},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-3-8-27b","name":"Qwen 3.8 27B","created":1786924800,"description":"Qwen 3.8 27B is a native vision-language dense model with 27B parameters. It improves coding, professional work, research, and long-horizon agentic tasks, with flexible thinking control and image and video understanding. It supports a native 262K-token context window.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.95e-7,"completion":3.5200000000000006e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.12976128,"max_completion_cost":0.23068672000000004,"max_cost":0.32800768},"sats_pricing":{"prompt":0.000621088397817784,"completion":0.004416628606704242,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":162.81459695754518,"max_completion_cost":289.4481723689692,"max_cost":411.55912008712806},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-3-8-flash","name":"Qwen 3.8 Flash","created":1788998400,"description":"Qwen 3.8 Flash is a multimodal model in the Qwen family, pairing strong reasoning and generation with remarkable speed. It natively supports a 1M-token context window, so it can process long documents, entire codebases, and complex conversations in a single pass. It excels at coding assistance, agentic workflows, and visual understanding, accepting text, image, and video input, and its thinking mode can be turned on or off per request.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.5400000000000003e-7,"completion":5.39e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5400000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.15400000000000003,"max_completion_cost":0.070647808,"max_cost":0.20446272000000004},"sats_pricing":{"prompt":0.0001932275015433106,"completion":0.0006762962554015871,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00001932275015433106,"input_cache_write":0.0,"max_prompt_cost":193.2275015433106,"max_completion_cost":88.64350278799682,"max_cost":256.5442892490226},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-3-7-max","name":"Qwen 3.7 Max","created":1779408000,"description":"Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.9700000000000004e-6,"completion":8.855000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.97e-7,"input_cache_write":3.6850000000000003e-6,"max_prompt_cost":2.97,"max_completion_cost":0.5803212800000002,"max_cost":3.3556793600000003},"sats_pricing":{"prompt":0.003726530386906704,"completion":0.01111058133874036,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00037265303869067043,"input_cache_write":0.004623658072643503,"max_prompt_cost":3726.530386906704,"max_completion_cost":728.1430586156882,"max_cost":4210.451550086074},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-3-7-plus","name":"Qwen 3.7 Plus","created":1780358400,"description":"Qwen 3.7 Plus, the successor to Qwen 3.6 Plus, is a reasoning model from Alibaba with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.500000000000001e-8,"input_cache_write":6.875000000000001e-7,"max_prompt_cost":0.55,"max_completion_cost":0.1441792,"max_cost":0.6581344},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0008626227747469223,"max_prompt_cost":690.0982197975378,"max_completion_cost":180.90510773060575,"max_cost":825.777050595492},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-3-6-plus","name":"Qwen 3.6 Plus Uncensored","created":1775433600,"description":"Qwen 3.6 Plus Uncensored is an uncensored variant of Alibaba's Qwen 3.6 Plus, a reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.875000000000001e-7,"completion":4.125e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.875e-8,"input_cache_write":8.580000000000001e-7,"max_prompt_cost":0.6875000000000001,"max_completion_cost":0.270336,"max_cost":0.9127800000000001},"sats_pricing":{"prompt":0.0008626227747469223,"completion":0.0051757366484815335,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008626227747469223,"input_cache_write":0.0010765532228841589,"max_prompt_cost":862.6227747469223,"max_completion_cost":339.1970769948858,"max_cost":1145.2870055759938},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-6-27b","name":"Qwen 3.6 27B","created":1776988800,"description":"The Qwen 3.6 27B native vision-language dense model builds upon the 3.5-27B version, with key improvements in agentic coding capabilities and enhanced STEM reasoning and inference skills. In the vision modality, it demonstrates significant advances in spatial intelligence, object localization, and detection, while video understanding, document OCR, and visual agent capabilities continue to improve steadily.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.575e-7,"completion":3.575e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.09152,"max_completion_cost":0.2342912,"max_cost":0.30238208},"sats_pricing":{"prompt":0.00044856384286839955,"completion":0.0044856384286839955,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":114.83234377431029,"max_completion_cost":293.97080006223433,"max_cost":379.40606383032116},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-6-35b-a3b","name":"Qwen 3.6 35B A3B","created":1784505600,"description":"Qwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1000000000000002e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.028160000000000004,"max_completion_cost":0.0720896,"max_cost":0.09304064000000001},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":35.33302885363394,"max_completion_cost":90.45255386530287,"max_cost":116.74032733240652},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-5-397b-a17b","name":"Qwen 3.5 397B","created":1771200000,"description":"Qwen 3.5 is a reasoning model from Alibaba featuring a 397B parameter Mixture-of-Experts architecture with 17B active parameters. It excels at complex reasoning, coding, and general knowledge tasks.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.950000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1056,"max_completion_cost":0.16220160000000003,"max_cost":0.24076800000000004},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.00621088397817784,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":132.49885820112723,"max_completion_cost":203.51824619693147,"max_cost":302.09739669857015},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-5-35b-a3b","name":"Qwen 3.5 35B A3B","created":1771977600,"description":"Qwen 3.5 35B A3B is a highly efficient MoE model with 35B total parameters and only 3B active parameters. It surpasses the larger Qwen3-235B-A22B while being 6.7x smaller, excelling at reasoning, coding, and general knowledge tasks.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.500000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.04224,"max_completion_cost":0.0180224,"max_cost":0.057559040000000006},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":52.9995432804509,"max_completion_cost":22.61313846632572,"max_cost":72.22071097682776},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen 3 235B A22B Thinking 2507","created":1745903059,"description":"Reasons step by step before it answers. Built for in-depth research and handling long, complex documents. Ideal for technical work and high-precision tasks.","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.95e-7,"completion":3.85e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.06336,"max_completion_cost":0.0630784,"max_cost":0.11832832000000001},"sats_pricing":{"prompt":0.000621088397817784,"completion":0.0048306875385827645,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":79.49931492067634,"max_completion_cost":79.14598463214001,"max_cost":148.4693872429698},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen 3 235B A22B Instruct 2507","created":1745903059,"description":"Answers directly, without a reasoning step. Built for in-depth research and handling long, complex documents. Ideal for technical work and high-precision tasks.","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":8.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02112,"max_completion_cost":0.0135168,"max_cost":0.03193344},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0010351473296963066,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":26.49977164022545,"max_completion_cost":16.959853849744288,"max_cost":40.06765472002088},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-next-80b","name":"Qwen 3 Next 80b","created":1745903059,"description":"Optimized for speed and efficiency.","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.85e-7,"completion":2.09e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.09856000000000001,"max_completion_cost":0.03424256,"max_cost":0.12649472},"sats_pricing":{"prompt":0.00048306875385827644,"completion":0.0026223732352306434,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":123.66560098771878,"max_completion_cost":42.96496308601886,"max_cost":158.71596561052363},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-vl-235b-a22b","name":"Qwen3 VL 235B","created":1768521600,"description":"Qwen3-VL 235B vision-language model with MoE architecture. The largest model in the Qwen3-VL series, with superior visual perception, OCR, and multimodal reasoning.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.3100000000000002e-7,"completion":2.09e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":0.029568,"max_completion_cost":0.03424256,"max_cost":0.060025856},"sats_pricing":{"prompt":0.0002898412523149659,"completion":0.0026223732352306434,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":37.09968029631563,"max_completion_cost":42.96496308601886,"max_cost":75.3158843044061},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-coder-480b-a35b-instruct-turbo","name":"Qwen 3 Coder 480B Turbo","created":1769472000,"description":"Turbo variant of Qwen3 Coder 480B, optimized for faster inference on code tasks.","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.85e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.09856000000000001,"max_completion_cost":0.1081344,"max_cost":0.18146304000000002},"sats_pricing":{"prompt":0.00048306875385827644,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":123.66560098771878,"max_completion_cost":135.6788307979543,"max_cost":227.68603793281707},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"google-gemma-4-26b-a4b-it","name":"Google Gemma 4 26B A4B Instruct","created":1775088000,"description":"Gemma 4 26B A4B is a Mixture-of-Experts model from Google DeepMind with 26B total parameters and only 4B active per token, offering fast inference at high quality. It handles text, image, and video input, supports 256K context, function calling, and reasoning with configurable thinking modes.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.4300000000000002e-7,"completion":4.400000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.500000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.03660800000000001,"max_completion_cost":0.007208960000000001,"max_cost":0.041474048000000006},"sats_pricing":{"prompt":0.00017942553714735983,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":45.93293750972412,"max_completion_cost":9.045255386530288,"max_cost":52.03848489563207},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"google-gemma-4-31b-it","name":"Google Gemma 4 31B Instruct","created":1775174400,"description":"Gemma 4 31B is a dense model from Google DeepMind with 31B parameters, delivering frontier-level reasoning performance. It handles text, image, and video input, supports 256K context, function calling, and configurable thinking modes.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":3.9600000000000005e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.900000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.033791999999999996,"max_completion_cost":0.006488064000000001,"max_cost":0.038117376},"sats_pricing":{"prompt":0.00016562357275140904,"completion":0.0004968707182542272,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001242176795635568,"input_cache_write":0.0,"max_prompt_cost":42.399634624360715,"max_completion_cost":8.140729847877259,"max_cost":47.82678785627889},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-4-uncensored","name":"Gemma 4 Uncensored","created":1776038400,"description":"Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token. Fine-tuned for uncensored chat without content filtering, it supports 256K context, coding, and general-purpose conversation.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.7875e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04576,"max_completion_cost":0.0045056,"max_cost":0.04880128},"sats_pricing":{"prompt":0.00022428192143419978,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":57.416171887155144,"max_completion_cost":5.65328461658143,"max_cost":61.232139003347605},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":8192,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"google-gemma-3-27b-it","name":"Google Gemma 3 27B Instruct","created":1762214400,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's open source model, successor to Gemma 2.","context_length":198000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":2.2000000000000004e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.026136,"max_completion_cost":0.0036044800000000006,"max_cost":0.027577791999999997},"sats_pricing":{"prompt":0.00016562357275140904,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":32.793467404778994,"max_completion_cost":4.522627693265144,"max_cost":34.602518482085046},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-4-3","name":"Grok 4.3","created":1776470400,"description":"Grok 4.3 is a reasoning model from xAI with function calling, structured outputs, and a 1M-token context window. Suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.562e-6,"completion":3.113e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.5300000000000006e-7,"input_cache_write":0.0,"max_prompt_cost":1.562,"max_completion_cost":0.099616,"max_cost":1.611632},"sats_pricing":{"prompt":0.001959878944225007,"completion":0.0039059559240540638,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003174451811068674,"input_cache_write":0.0,"max_prompt_cost":1959.8789442250072,"max_completion_cost":124.99058956973003,"max_cost":2022.1534075795369},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-4-5","name":"Grok 4.5","created":1783382400,"description":"Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window.","context_length":500000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.497e-6,"completion":7.48e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.7400000000000004e-7,"input_cache_write":0.0,"max_prompt_cost":1.2485,"max_completion_cost":0.23936000000000002,"max_cost":1.407956},"sats_pricing":{"prompt":0.0031330459178808214,"completion":0.009385335789246513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00046926678946232573,"input_cache_write":0.0,"max_prompt_cost":1566.5229589404105,"max_completion_cost":300.3307452558884,"max_cost":1766.5962348241128},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":32000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-4-6","name":"Grok 4.6","created":1786320000,"description":"Grok 4.6 is xAI's multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.","context_length":500000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.497e-6,"completion":7.48e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.27e-7,"input_cache_write":0.0,"max_prompt_cost":1.2485,"max_completion_cost":1.496,"max_cost":2.2451},"sats_pricing":{"prompt":0.0031330459178808214,"completion":0.009385335789246513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000786711970569193,"input_cache_write":0.0,"max_prompt_cost":1566.5229589404105,"max_completion_cost":1877.0671578493027,"max_cost":2816.9809332135487},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":200000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-4-7","name":"Grok 4.7","created":1789516800,"description":"Grok 4.7, the successor to Grok 4.6, is xAI's multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.","context_length":500000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.497e-6,"completion":7.48e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.27e-7,"input_cache_write":0.0,"max_prompt_cost":1.2485,"max_completion_cost":1.496,"max_cost":2.2451},"sats_pricing":{"prompt":0.0031330459178808214,"completion":0.009385335789246513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000786711970569193,"input_cache_write":0.0,"max_prompt_cost":1566.5229589404105,"max_completion_cost":1877.0671578493027,"max_cost":2816.9809332135487},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":200000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-4-20","name":"Grok 4.20","created":1773273600,"description":"Grok 4.20 is xAI's multimodal reasoning model with strong tool use, structured output support, and a 2M-token context window.","context_length":2000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.562e-6,"completion":3.113e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.5300000000000006e-7,"input_cache_write":0.0,"max_prompt_cost":3.124,"max_completion_cost":0.398464,"max_cost":3.322528},"sats_pricing":{"prompt":0.001959878944225007,"completion":0.0039059559240540638,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003174451811068674,"input_cache_write":0.0,"max_prompt_cost":3919.7578884500144,"max_completion_cost":499.96235827892014,"max_cost":4168.855741868134},"per_request_limits":null,"top_provider":{"context_length":2000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-4-20-multi-agent","name":"Grok 4.20 Multi-Agent","created":1773273600,"description":"Grok 4.20 Multi-Agent is a variant of xAI Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.","context_length":2000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.562e-6,"completion":3.113e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.5300000000000006e-7,"input_cache_write":0.0,"max_prompt_cost":3.124,"max_completion_cost":0.398464,"max_cost":3.322528},"sats_pricing":{"prompt":0.001959878944225007,"completion":0.0039059559240540638,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003174451811068674,"input_cache_write":0.0,"max_prompt_cost":3919.7578884500144,"max_completion_cost":499.96235827892014,"max_cost":4168.855741868134},"per_request_limits":null,"top_provider":{"context_length":2000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-build-0-1","name":"Grok Build 0.1","created":1779321600,"description":"xAI's fast coding model trained specifically for agentic coding, currently in early access.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000004e-7,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":0.1441792,"max_cost":0.35368960000000005},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":353.33028853633937,"max_completion_cost":180.90510773060575,"max_cost":443.78284240164226},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-small-3-2-24b-instruct","name":"Mistral Small 3.2 24B Instruct","created":1768435200,"description":"Mistral Small 3.2 is a 24B parameter model optimized for efficiency and performance. Ideal for general-purpose tasks with balanced speed and capability.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.03125e-7,"completion":2.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0264,"max_completion_cost":0.0045056,"max_cost":0.029216},"sats_pricing":{"prompt":0.00012939341621203833,"completion":0.0003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":33.12471455028181,"max_completion_cost":5.65328461658143,"max_cost":36.658017435645206},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","created":1771459200,"description":"Gemini 3.1 Pro is an evolution of Google's flagship frontier model with 1M context, advancing high-precision multimodal reasoning across text, image, and code.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":5.5e-7,"max_prompt_cost":2.7500000000000004,"max_completion_cost":0.540672,"max_cost":3.2005600000000003},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0006900982197975378,"max_prompt_cost":3450.4910989876894,"max_completion_cost":678.3941539897716,"max_cost":4015.819560645832},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-3-5-flash","name":"Gemini 3.5 Flash","created":1779408000,"description":"Gemini 3.5 Flash is a high speed, high value thinking model with 1M context, designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.7050000000000002e-6,"completion":0.000010395,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7050000000000002e-7,"input_cache_write":9.46e-8,"max_prompt_cost":1.7050000000000003,"max_completion_cost":0.68124672,"max_cost":2.27450784},"sats_pricing":{"prompt":0.002139304481372367,"completion":0.013042856354173463,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00021393044813723672,"input_cache_write":0.0001186968938051765,"max_prompt_cost":2139.3044813723673,"max_completion_cost":854.7766340271121,"max_cost":2853.8796569082597},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","created":1766102400,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":7.7e-7,"completion":4.125e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.700000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.19712000000000002,"max_completion_cost":0.270336,"max_cost":0.41699328},"sats_pricing":{"prompt":0.0009661375077165529,"completion":0.0051757366484815335,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000966137507716553,"input_cache_write":0.0,"max_prompt_cost":247.33120197543755,"max_completion_cost":339.1970769948858,"max_cost":523.2114912646113},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-fable-5","name":"Anthropic: Claude Fable 5","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":6.5000000000000004e-6,"completion":0.000032500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":6.5e-7,"input_cache_write":8.125000000000001e-6,"max_prompt_cost":6.500000000000001,"max_completion_cost":4.16,"max_cost":9.828},"sats_pricing":{"prompt":0.0081557062339709,"completion":0.040778531169854505,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.0008155706233970901,"input_cache_write":0.010194632792463626,"max_prompt_cost":8155.706233970902,"max_completion_cost":5219.651989741376,"max_cost":12331.427825764002},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-5-fable-20260609","alias_ids":["claude-fable-5"],"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","created":1787961600,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities, and tends to be more concise in its plans and summaries.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.000000000000002,"max_completion_cost":7.040000000000001,"max_cost":16.632},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.017252455494938448,"max_prompt_cost":13801.964395950758,"max_completion_cost":8833.257213408484,"max_cost":20868.570166677542},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-5","name":"Anthropic: Claude Opus 5","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.2500000000000002e-6,"completion":0.000016250000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":3.25e-7,"input_cache_write":4.0625000000000005e-6,"max_prompt_cost":3.2500000000000004,"max_completion_cost":2.08,"max_cost":4.914},"sats_pricing":{"prompt":0.00407785311698545,"completion":0.020389265584927253,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.00040778531169854504,"input_cache_write":0.005097316396231813,"max_prompt_cost":4077.853116985451,"max_completion_cost":2609.825994870688,"max_cost":6165.713912882001},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-opus-5-20260723","alias_ids":["claude-opus-5"],"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-5-fast","name":"Claude Opus 5 Fast","created":1784764800,"description":"Claude Opus 5 (Fast) is a speed-optimized variant of Claude Opus 5, offering the same 1M token context window and strong performance across agentic coding, professional knowledge work, and long-horizon reasoning — with lower latency.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.000000000000002,"max_completion_cost":7.040000000000001,"max_cost":16.632},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0013801964395950756,"input_cache_write":0.017252455494938448,"max_prompt_cost":13801.964395950758,"max_completion_cost":8833.257213408484,"max_cost":20868.570166677542},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","created":1789689600,"description":"Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work, with a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000004e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.4,"max_completion_cost":2.8160000000000003,"max_cost":6.652800000000001},"sats_pricing":{"prompt":0.005520785758380302,"completion":0.027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.006900982197975378,"max_prompt_cost":5520.7857583803025,"max_completion_cost":3533.3028853633937,"max_cost":8347.428066671018},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-5-5-fast","name":"Claude Opus 5.5 Fast","created":1790380800,"description":"Claude Opus 5.5 Fast serves the same Opus 5.5 model with faster output generation, a 1M token context window, up to 128K output tokens, adaptive thinking, vision, and tool calling.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.8e-6,"completion":0.000044000000000000006,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.400000000000001e-7,"input_cache_write":0.000011000000000000001,"max_prompt_cost":8.8,"max_completion_cost":5.632000000000001,"max_cost":13.305600000000002},"sats_pricing":{"prompt":0.011041571516760605,"completion":0.055207857583803026,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005520785758380303,"input_cache_write":0.013801964395950756,"max_prompt_cost":11041.571516760605,"max_completion_cost":7066.605770726787,"max_cost":16694.856133342037},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","created":1779926400,"description":"Claude Opus 4.8 is the successor to Opus 4.7 in Anthropic's Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.008626227747469224,"max_prompt_cost":6900.982197975379,"max_completion_cost":4416.628606704242,"max_cost":10434.285083338771},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-4-8-fast","name":"Claude Opus 4.8 Fast","created":1779926400,"description":"Claude Opus 4.8 (Fast) is a speed-optimized variant of Claude Opus 4.8, offering the same 1M token context window and strong performance across long-horizon agentic work and complex coding — with lower latency.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.000000000000002,"max_completion_cost":7.040000000000001,"max_cost":16.632},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0013801964395950756,"input_cache_write":0.017252455494938448,"max_prompt_cost":13801.964395950758,"max_completion_cost":8833.257213408484,"max_cost":20868.570166677542},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","created":1776297600,"description":"Claude Opus 4.7 is a model from Anthropic for complex reasoning and agentic coding. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.008626227747469224,"max_prompt_cost":6900.982197975379,"max_completion_cost":4416.628606704242,"max_cost":10434.285083338771},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","created":1770249600,"description":"Claude Opus 4.6 is a reasoning model from Anthropic, building on Opus 4.5 with enhanced performance across complex software engineering, agentic workflows, and long-horizon tasks. It features a 1M token context window, improved multimodal capabilities, and stronger robustness to prompt injection.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.008626227747469224,"max_prompt_cost":6900.982197975379,"max_completion_cost":4416.628606704242,"max_cost":10434.285083338771},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-4-5","name":"Claude Opus 4.5","created":1764979200,"description":"Claude Opus 4.5 is Anthropic's frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.","context_length":198000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":1.0890000000000002,"max_completion_cost":0.9011200000000001,"max_cost":1.8098960000000002},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.008626227747469224,"max_prompt_cost":1366.394475199125,"max_completion_cost":1130.656923316286,"max_cost":2270.9200138521537},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.3e-6,"completion":6.5000000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":1.3e-7,"input_cache_write":1.6250000000000001e-6,"max_prompt_cost":1.3,"max_completion_cost":0.8320000000000001,"max_cost":1.9656},"sats_pricing":{"prompt":0.0016311412467941802,"completion":0.0081557062339709,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.000163114124679418,"input_cache_write":0.002038926558492725,"max_prompt_cost":1631.1412467941802,"max_completion_cost":1043.9303979482754,"max_cost":2466.2855651528002},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-sonnet-5-20260630","alias_ids":["claude-sonnet-5"],"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","created":1790380800,"description":"Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000002e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.4080000000000001,"max_cost":3.3264000000000005},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.003450491098987689,"max_prompt_cost":2760.3928791901512,"max_completion_cost":1766.6514426816968,"max_cost":4173.714033335509},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","created":1791331200,"description":"Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1000000000000002e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.11000000000000001,"max_completion_cost":0.0704,"max_cost":0.16632000000000002},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.00017252455494938445,"max_prompt_cost":138.01964395950756,"max_completion_cost":88.33257213408484,"max_cost":208.68570166677543},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","created":1771286400,"description":"Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features a 1M token context window and 64K max output tokens.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":4.125e-6,"max_prompt_cost":3.3000000000000003,"max_completion_cost":1.056,"max_cost":4.1448},"sats_pricing":{"prompt":0.004140589318785227,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00041405893187852267,"input_cache_write":0.0051757366484815335,"max_prompt_cost":4140.589318785227,"max_completion_cost":1324.9885820112725,"max_cost":5200.5801843942445},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-oss-120b","name":"OpenAI GPT OSS 120B","created":1762387200,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":7.700000000000001e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.009856000000000002,"max_completion_cost":0.00540672,"max_cost":0.014001152000000001},"sats_pricing":{"prompt":0.0000966137507716553,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":12.36656009877188,"max_completion_cost":6.783941539897715,"max_cost":17.56758194602679},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k3-1-pro","name":"Kimi K3.1 Pro","created":1792713600,"description":"Kimi K3.1 Pro is Moonshot AI's flagship multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, agentic workflows, financial research, and 3D modeling through CAD code.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000004e-7,"input_cache_write":0.0,"max_prompt_cost":2.2,"max_completion_cost":1.4417920000000002,"max_cost":3.3534336000000002},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":2760.3928791901512,"max_completion_cost":1809.0510773060576,"max_cost":4207.633741034997},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k3-1-pro-highspeed","name":"Kimi K3.1 Pro Highspeed","created":1792713600,"description":"Kimi K3.1 Pro Highspeed is the faster variant of Kimi K3.1 Pro, Moonshot AI's flagship multimodal reasoning model. It offers the same quality and 1M-token context window with substantially higher output speed for latency-sensitive coding and agentic workflows.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-7,"input_cache_write":0.0,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.6044800000000006,"max_cost":8.383584},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005175736648481533,"input_cache_write":0.0,"max_prompt_cost":6900.982197975379,"max_completion_cost":4522.627693265144,"max_cost":10519.084352587493},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k3","name":"Kimi K3","created":1784160000,"description":"Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.125e-6,"completion":0.000020625,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-7,"input_cache_write":0.0,"max_prompt_cost":4.125,"max_completion_cost":2.70336,"max_cost":6.287688},"sats_pricing":{"prompt":0.0051757366484815335,"completion":0.025878683242407666,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005175736648481533,"input_cache_write":0.0,"max_prompt_cost":5175.736648481533,"max_completion_cost":3391.9707699488577,"max_cost":7889.31326444062},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k3-fast-api","name":"Kimi K3 Fast","created":1785715200,"description":"Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.950000000000001e-6,"completion":0.000024750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.95e-7,"input_cache_write":0.0,"max_prompt_cost":4.950000000000001,"max_completion_cost":3.2440320000000002,"max_cost":7.5452256},"sats_pricing":{"prompt":0.00621088397817784,"completion":0.0310544198908892,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000621088397817784,"input_cache_write":0.0,"max_prompt_cost":6210.883978177841,"max_completion_cost":4070.364923938629,"max_cost":9467.175917328743},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2-7-code","name":"Kimi K2.7 Code","created":1781308800,"description":"Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image input, and targets long-horizon software engineering, agentic task decomposition, and multi-turn coding workflows with 256K context.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":3.85e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7600000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.2112,"max_completion_cost":0.2523136,"max_cost":0.40944640000000004},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.0048306875385827645,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002208314303352121,"input_cache_write":0.0,"max_prompt_cost":264.99771640225447,"max_completion_cost":316.58393852856005,"max_cost":513.7422395318374},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2-6","name":"Kimi K2.6","created":1776643200,"description":"Kimi K2.6 is an open-source, native multimodal agentic model from Moonshot AI with 1T total parameters and 32B active parameters. It excels at long-horizon coding, coding-driven design, agent swarm orchestration, and proactive autonomous execution with a 256K-token context window.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":3.85e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7600000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.2112,"max_completion_cost":0.2523136,"max_cost":0.40944640000000004},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.0048306875385827645,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002208314303352121,"input_cache_write":0.0,"max_prompt_cost":264.99771640225447,"max_completion_cost":316.58393852856005,"max_cost":513.7422395318374},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2-5","name":"Kimi K2.5","created":1769548800,"description":"Kimi K2.5 is an open reasoning model from Moonshot AI, featuring trillion-parameter Mixture-of-Experts architecture with 32B active parameters and a 256K-token context window.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.160000000000001e-7,"completion":3.85e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.42e-7,"input_cache_write":0.0,"max_prompt_cost":0.15769600000000003,"max_completion_cost":0.2523136,"max_cost":0.36963942400000005},"sats_pricing":{"prompt":0.0007729100061732424,"completion":0.0048306875385827645,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003036432167109166,"input_cache_write":0.0,"max_prompt_cost":197.86496158035007,"max_completion_cost":316.58393852856005,"max_cost":463.7954699443405},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"xiaomi-mimo-v2-5","name":"MiMo-V2.5","created":1781136000,"description":"MiMo-V2.5 is Xiaomi's native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding in a unified architecture. Built on a sparse Mixture-of-Experts backbone with 310B total and 15B active parameters, it delivers long-context reasoning up to 1M tokens, function calling, and multimodal perception.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.400000000000001e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.800000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.44000000000000006,"max_completion_cost":0.1441792,"max_cost":0.5553433600000001},"sats_pricing":{"prompt":0.0005520785758380303,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00011041571516760605,"input_cache_write":0.0,"max_prompt_cost":552.0785758380302,"max_completion_cost":180.90510773060575,"max_cost":696.8026620225148},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"xiaomi-mimo-v2-6-flash","name":"MiMo-V2.6-Flash","created":1790553600,"description":"MiMo-V2.6-Flash is Xiaomi's efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a 1M-token context window. Trained with mixed reinforcement learning across coding, general agents, visual, and cybersecurity tasks, it is built for long-horizon coding, tool use, and computer use.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.925e-7,"completion":3.85e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-9,"input_cache_write":0.0,"max_prompt_cost":0.1925,"max_completion_cost":0.05046272,"max_cost":0.21773135999999998},"sats_pricing":{"prompt":0.00024153437692913822,"completion":0.00048306875385827644,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.1757366484815325e-6,"input_cache_write":0.0,"max_prompt_cost":241.5343769291382,"max_completion_cost":63.31678770571201,"max_cost":273.19277078199417},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","created":1776988800,"description":"DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.815e-6,"completion":3.6311000000000007e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.6300000000000006e-7,"input_cache_write":0.0,"max_prompt_cost":1.815,"max_completion_cost":0.9518710784000002,"max_cost":2.2910797184000002},"sats_pricing":{"prompt":0.0022773241253318745,"completion":0.004556028447103345,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00045546482506637496,"input_cache_write":0.0,"max_prompt_cost":2277.3241253318743,"max_completion_cost":1194.3355212374593,"max_cost":2874.672791058335},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash 0423","created":1776988800,"description":"DeepSeek V4 Flash is an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.5180000000000002e-7,"completion":3.025e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.0800000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.15180000000000002,"max_completion_cost":0.07929856,"max_cost":0.19130510080000002},"sats_pricing":{"prompt":0.00019046710866412044,"completion":0.0003795540208886458,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003864550030866212,"input_cache_write":0.0,"max_prompt_cost":190.46710866412045,"max_completion_cost":99.49780925183316,"max_cost":240.0351081823064},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","created":1785456000,"description":"DeepSeek V4 Flash 0731 follows the 0423 release of DeepSeek V4 Flash, an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.4300000000000002e-7,"completion":2.8600000000000005e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.0800000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.14300000000000002,"max_completion_cost":0.07497318400000001,"max_cost":0.18048659200000003},"sats_pricing":{"prompt":0.00017942553714735983,"completion":0.00035885107429471967,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003864550030866212,"input_cache_write":0.0,"max_prompt_cost":179.42553714735982,"max_completion_cost":94.07065601991499,"max_cost":226.46086515731733},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","created":1788998400,"description":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-9,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.34603008,"max_cost":0.58952256},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000010351473296963065,"input_cache_write":0.0,"max_prompt_cost":414.0589318785227,"max_completion_cost":434.1722585534538,"max_cost":739.688125793613},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek v4.1 Flash (1017)","created":1792195200,"description":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-9,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.34603008,"max_cost":0.58952256},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000010351473296963065,"input_cache_write":0.0,"max_prompt_cost":414.0589318785227,"max_completion_cost":434.1722585534538,"max_cost":739.688125793613},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-1-flash-uncensored","name":"DeepSeek V4.1 Flash Uncensored","created":1792713600,"description":"DeepSeek V4.1 Flash Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.6300000000000006e-7,"completion":1.4520000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.075000000000002e-9,"input_cache_write":0.0,"max_prompt_cost":0.36300000000000004,"max_completion_cost":0.19031654400000003,"max_cost":0.5057374080000001},"sats_pricing":{"prompt":0.00045546482506637496,"completion":0.0018218593002654999,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000011386620626659376,"input_cache_write":0.0,"max_prompt_cost":455.46482506637494,"max_completion_cost":238.7947422043996,"max_cost":634.5608817196747},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-1-flash-1017-uncensored","name":"DeepSeek V4.1 Flash 1017 Uncensored","created":1793059200,"description":"DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.6300000000000006e-7,"completion":1.4520000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.075000000000002e-9,"input_cache_write":0.0,"max_prompt_cost":0.36300000000000004,"max_completion_cost":0.19031654400000003,"max_cost":0.5057374080000001},"sats_pricing":{"prompt":0.00045546482506637496,"completion":0.0018218593002654999,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000011386620626659376,"input_cache_write":0.0,"max_prompt_cost":455.46482506637494,"max_completion_cost":238.7947422043996,"max_cost":634.5608817196747},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","created":1764806400,"description":"DeepSeek-V3.2 is an efficient large language model with DeepSeek Sparse Attention (DSA) for long contexts. It features strong reasoning and tool-use skills, achieving top results on the 2025 IMO and IOI.","context_length":160000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.6300000000000006e-7,"completion":5.28e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7600000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.05808000000000001,"max_completion_cost":0.017301504,"max_cost":0.06348672000000001},"sats_pricing":{"prompt":0.00045546482506637496,"completion":0.0006624942910056362,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002208314303352121,"input_cache_write":0.0,"max_prompt_cost":72.87437201062,"max_completion_cost":21.708612927672686,"max_cost":79.65831355051772},"per_request_limits":null,"top_provider":{"context_length":160000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"seed-2-1-turbo","name":"Seed 2.1 Turbo","created":1782604800,"description":"Seed 2.1 Turbo (Dola-Seed-2.1) is ByteDance’s next-generation multimodal model for the coding and agent era, with engineering-grade code delivery, long-horizon agent execution, and upgraded GUI and video understanding. Supports text, image, and video inputs with a 256K context window.","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.875000000000001e-7,"completion":3.4375000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":0.17600000000000002,"max_completion_cost":0.22528000000000004,"max_cost":0.35622400000000004},"sats_pricing":{"prompt":0.0008626227747469223,"completion":0.004313113873734612,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0,"max_prompt_cost":220.8314303352121,"max_completion_cost":282.6642308290715,"max_cost":446.9628149984693},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","created":1786665600,"description":"DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.815e-6,"completion":5.445e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.8150000000000003e-7,"input_cache_write":0.0,"max_prompt_cost":1.815,"max_completion_cost":1.42737408,"max_cost":2.76658272},"sats_pricing":{"prompt":0.0022773241253318745,"completion":0.006831972375995624,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00022773241253318748,"input_cache_write":0.0,"max_prompt_cost":2277.3241253318743,"max_completion_cost":1790.9605665329968,"max_cost":3471.2978363538728},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v4-flash-0731-fast","name":"DeepSeek V4 Flash 0731 Fast","created":1786233600,"description":"DeepSeek V4 Flash 0731 follows the 0423 release of DeepSeek V4 Flash, an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.85e-7,"completion":7.7e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.625e-8,"input_cache_write":0.0,"max_prompt_cost":0.385,"max_completion_cost":0.02523136,"max_cost":0.39761568},"sats_pricing":{"prompt":0.00048306875385827644,"completion":0.0009661375077165529,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00012076718846456911,"input_cache_write":0.0,"max_prompt_cost":483.0687538582764,"max_completion_cost":31.658393852856005,"max_cost":498.89795078470445},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"aion-labs-aion-3-0","name":"Aion 3.0","created":1783468800,"description":"Aion 3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.125e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.03125e-6,"input_cache_write":0.0,"max_prompt_cost":0.528,"max_completion_cost":0.270336,"max_cost":0.663168},"sats_pricing":{"prompt":0.0051757366484815335,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0012939341621203834,"input_cache_write":0.0,"max_prompt_cost":662.4942910056362,"max_completion_cost":339.1970769948858,"max_cost":832.0928295030791},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"aion-labs-aion-3-0-mini","name":"Aion 3.0 Mini","created":1783468800,"description":"Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":9.625e-7,"completion":1.925e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.475e-7,"input_cache_write":0.0,"max_prompt_cost":0.12320000000000002,"max_completion_cost":0.0630784,"max_cost":0.15473920000000002},"sats_pricing":{"prompt":0.0012076718846456911,"completion":0.0024153437692913822,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000310544198908892,"input_cache_write":0.0,"max_prompt_cost":154.5820012346485,"max_completion_cost":79.14598463214001,"max_cost":194.15499355071847},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"aion-labs-aion-3-5","name":"Aion 3.5","created":1790121600,"description":"Aion 3.5, the successor to Aion 3.0, is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models, with a longer context window. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.125e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.03125e-6,"input_cache_write":0.0,"max_prompt_cost":1.081344,"max_completion_cost":0.270336,"max_cost":1.2165120000000003},"sats_pricing":{"prompt":0.0051757366484815335,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0012939341621203834,"input_cache_write":0.0,"max_prompt_cost":1356.788307979543,"max_completion_cost":339.1970769948858,"max_cost":1526.3868464769862},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"aion-labs-aion-3-5-mini","name":"Aion 3.5 Mini","created":1790121600,"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":9.625e-7,"completion":1.925e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.475e-7,"input_cache_write":0.0,"max_prompt_cost":0.2523136,"max_completion_cost":0.0630784,"max_cost":0.2838528},"sats_pricing":{"prompt":0.0012076718846456911,"completion":0.0024153437692913822,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000310544198908892,"input_cache_write":0.0,"max_prompt_cost":316.58393852856005,"max_completion_cost":79.14598463214001,"max_cost":356.15693084463004},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"abliteration-abliterated-model-large-v2","name":"Abliterated Large V2","created":1790812800,"description":"Abliterated Large V2 is Abliteration AI's unrestricted reasoning model, based on GLM-5.3 and further abliterated and fine-tuned. Text-only with 1M context, for harder reasoning and evaluation workloads. Always reasons; depth can be set to low, high, or max.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":0.0,"max_prompt_cost":3.3000000000000003,"max_completion_cost":0.18022400000000002,"max_cost":3.3720896000000002},"sats_pricing":{"prompt":0.004140589318785227,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00041405893187852267,"input_cache_write":0.0,"max_prompt_cost":4140.589318785227,"max_completion_cost":226.1313846632572,"max_cost":4231.0418726505295},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"abliteration-abliterated-model-large-flash","name":"Abliterated Large Flash","created":1792713600,"description":"Abliterated Large Flash is Abliteration AI's unrestricted multimodal model, based on DeepSeek V4.1 Flash and further abliterated. It has 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":1.3750000000000002,"max_completion_cost":0.36044800000000005,"max_cost":1.5552240000000002},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0,"max_prompt_cost":1725.2455494938447,"max_completion_cost":452.2627693265144,"max_cost":1951.3769341571017},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.2-3b","name":"Meta Llama 3.2 3B","created":1740523679,"description":"Meta Llama 3.2 3B via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.3-70b","name":"Llama 3.3 70B","created":1743897600,"description":"Venice text model","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":7.7e-7,"completion":3.08e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.09856000000000001,"max_completion_cost":0.01261568,"max_cost":0.10802176000000001},"sats_pricing":{"prompt":0.0009661375077165529,"completion":0.0038645500308662115,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":123.66560098771878,"max_completion_cost":15.829196926428002,"max_cost":135.53749868253976},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"muse-wonder","name":"Muse Wonder","created":1791763200,"description":"Muse Wonder is a frontier reasoning model from Meta for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window. The model plans, delegates to sub-agents, calls tools in parallel, and recovers from errors so long-horizon work can run to completion without step-by-step direction.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":5.767168000000001,"max_completion_cost":3.6044800000000006,"max_cost":8.650752},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":7236.20430922423,"max_completion_cost":4522.627693265144,"max_cost":10854.306463836345},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"muse-spark-open","name":"Muse Spark Open","created":1792022400,"description":"Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.7187500000000003e-6,"completion":5.843750000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.0625e-7,"input_cache_write":0.0,"max_prompt_cost":1.8022400000000003,"max_completion_cost":0.7659520000000001,"max_cost":2.342912},"sats_pricing":{"prompt":0.002156556936867306,"completion":0.007332293585348839,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00025878683242407666,"input_cache_write":0.0,"max_prompt_cost":2261.313846632572,"max_completion_cost":961.058384818843,"max_cost":2939.708000622343},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-52","name":"GPT-5.2","created":1765584000,"description":"GPT-5.2 is a frontier-grade model in the GPT-5 series, offering stronger agentic and long context performance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.49280000000000007,"max_completion_cost":1.0092544,"max_cost":1.3758976},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00024153437692913822,"input_cache_write":0.0,"max_prompt_cost":618.328004938594,"max_completion_cost":1266.3357541142402,"max_cost":1726.371789788554},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-53-codex","name":"GPT-5.3 Codex","created":1771891200,"description":"GPT-5.3 Codex, the successor to GPT-5.2 Codex, is OpenAI's specialized coding model, optimized for advanced software development, code generation, and technical problem-solving. It supports a longer context window and longer outputs than GPT-5.2 Codex.","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.7700000000000001,"max_completion_cost":1.9712000000000003,"max_cost":2.4948000000000006},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00024153437692913822,"input_cache_write":0.0,"max_prompt_cost":966.137507716553,"max_completion_cost":2473.312019754376,"max_cost":3130.285525001632},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-54","name":"GPT-5.4","created":1772668800,"description":"GPT-5.4, the successor to GPT-5.2, is a frontier model in the GPT-5 series with a 1M+ context window, offering improved agentic and long context performance. It uses adaptive reasoning to dynamically allocate computation across tasks.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.7500000000000004,"max_completion_cost":2.162688,"max_cost":4.55224},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":3450.4910989876894,"max_completion_cost":2713.576615959086,"max_cost":5711.804945620261},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-54-pro","name":"GPT-5.4 Pro","created":1772668800,"description":"GPT-5.4 Pro builds on GPT-5.4's unified architecture with enhanced reasoning for complex, high-stakes tasks. It provides a 1M+ token context window (922K input, 128K output) and supports text and image inputs.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.000033,"completion":0.00019800000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":33.0,"max_completion_cost":25.344,"max_cost":54.120000000000005},"sats_pricing":{"prompt":0.04140589318785227,"completion":0.2484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":41405.89318785226,"max_completion_cost":31799.72596827054,"max_cost":67905.66482807772},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-54-mini","name":"GPT-5.4 Mini","created":1774569600,"description":"GPT-5.4 Mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use.","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.950000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.6336000000000002,"max_cost":0.8580000000000002},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.00621088397817784,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":414.0589318785227,"max_completion_cost":794.9931492067636,"max_cost":1076.5532228841591},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-55","name":"GPT-5.5","created":1776902400,"description":"GPT-5.5, the successor to GPT-5.4, is a frontier model in the GPT-5 series with a 1M+ context window, offering improved agentic and long context performance. It uses adaptive reasoning to dynamically allocate computation across tasks.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":5.500000000000001,"max_completion_cost":4.325376,"max_cost":9.10448},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.04140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":6900.982197975379,"max_completion_cost":5427.153231918172,"max_cost":11423.609891240521},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-55-pro","name":"GPT-5.5 Pro","created":1776988800,"description":"GPT-5.5 Pro, the successor to GPT-5.4 Pro, builds on GPT-5.5's unified architecture with enhanced reasoning for complex, high-stakes tasks. It provides a 1M+ token context window (922K input, 128K output) and supports text and image inputs.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.000033,"completion":0.00019800000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":33.0,"max_completion_cost":25.344,"max_cost":54.120000000000005},"sats_pricing":{"prompt":0.04140589318785227,"completion":0.2484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":41405.89318785226,"max_completion_cost":31799.72596827054,"max_cost":67905.66482807772},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-56-luna","name":"GPT-5.6 Luna","created":1783555200,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":2.75e-7,"max_prompt_cost":0.22000000000000003,"max_completion_cost":0.16896,"max_cost":0.3608},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0003450491098987689,"max_prompt_cost":276.0392879190151,"max_completion_cost":211.9981731218036,"max_cost":452.70443218718475},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-56-luna-pro","name":"GPT-5.6 Luna Pro","created":1783555200,"description":"GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":2.75e-7,"max_prompt_cost":0.22000000000000003,"max_completion_cost":0.16896,"max_cost":0.3608},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0003450491098987689,"max_prompt_cost":276.0392879190151,"max_completion_cost":211.9981731218036,"max_cost":452.70443218718475},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-56-terra","name":"GPT-5.6 Terra","created":1783555200,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000004e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.6896,"max_cost":3.608},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.016562357275140906,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2760.3928791901512,"max_completion_cost":2119.9817312180357,"max_cost":4527.044321871847},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-56-terra-pro","name":"GPT-5.6 Terra Pro","created":1783555200,"description":"GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000004e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.6896,"max_cost":3.608},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.016562357275140906,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2760.3928791901512,"max_completion_cost":2119.9817312180357,"max_cost":4527.044321871847},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-56-sol","name":"GPT-5.6 Sol","created":1783555200,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.400000000000001e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.4,"max_completion_cost":2.8160000000000003,"max_cost":6.652800000000001},"sats_pricing":{"prompt":0.005520785758380302,"completion":0.027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005520785758380303,"input_cache_write":0.006900982197975378,"max_prompt_cost":5520.7857583803025,"max_completion_cost":3533.3028853633937,"max_cost":8347.428066671018},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-56-sol-pro","name":"GPT-5.6 Sol Pro","created":1783555200,"description":"GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.400000000000001e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.4,"max_completion_cost":2.8160000000000003,"max_cost":6.652800000000001},"sats_pricing":{"prompt":0.005520785758380302,"completion":0.027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005520785758380303,"input_cache_write":0.006900982197975378,"max_prompt_cost":5520.7857583803025,"max_completion_cost":3533.3028853633937,"max_cost":8347.428066671018},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-6-astra","name":"GPT-6 Astra","created":1788566400,"description":"GPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with a 1.05M token context window (922K input, 128K output) and support for text and image inputs.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.55,"max_completion_cost":7.040000000000001,"max_cost":17.182000000000002},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0013801964395950756,"input_cache_write":0.017252455494938448,"max_prompt_cost":14492.062615748293,"max_completion_cost":8833.257213408484,"max_cost":21558.66838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-6-astra-pro","name":"GPT-6 Astra Pro","created":1788566400,"description":"GPT-6 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.55,"max_completion_cost":7.040000000000001,"max_cost":17.182000000000002},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0013801964395950756,"input_cache_write":0.017252455494938448,"max_prompt_cost":14492.062615748293,"max_completion_cost":8833.257213408484,"max_cost":21558.66838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-6-luna","name":"GPT-6 Luna","created":1790035200,"description":"GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks. It is suited for chat, classification, and lightweight agentic workflows, with a 1.05M token context window (922K input, 128K output), text and image inputs, and capable reasoning for its price tier.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1000000000000002e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.11550000000000002,"max_completion_cost":0.0704,"max_cost":0.17182000000000003},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.00017252455494938445,"max_prompt_cost":144.92062615748296,"max_completion_cost":88.33257213408484,"max_cost":215.58668386475082},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-6-sol","name":"GPT-6 Sol","created":1790035200,"description":"GPT-6 Sol is built for complex coding and agentic workflows. It is OpenAI's GPT-6 coding and agent model, with a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000004e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-61-sol","name":"GPT-6.1 Sol","created":1790640000,"description":"GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000002e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-61-sol-ultrafast","name":"GPT-6.1 Sol Ultrafast","created":1791417600,"description":"GPT-6.1 Sol Ultrafast is the same model served in OpenAI's Ultrafast mode, up to 8x faster. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0000132,"completion":0.000066,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-7,"input_cache_write":0.0000165,"max_prompt_cost":13.860000000000001,"max_completion_cost":8.448,"max_cost":20.6184},"sats_pricing":{"prompt":0.016562357275140906,"completion":0.08281178637570454,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0008281178637570453,"input_cache_write":0.020702946593926134,"max_prompt_cost":17390.475138897953,"max_completion_cost":10599.90865609018,"max_cost":25870.402063770096},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-61-terra","name":"GPT-6.1 Terra","created":1792972800,"description":"GPT-6.1 Terra is a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.500000000000001e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1449.2062615748293,"max_completion_cost":883.3257213408484,"max_cost":2155.866838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-4o-2024-11-20","name":"GPT-4o","created":1772236800,"description":"OpenAI's multimodal model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0017252455494938446,"input_cache_write":0.0,"max_prompt_cost":441.6628606704242,"max_completion_cost":226.1313846632572,"max_cost":611.2613991678671},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"openai-gpt-4o-mini-2024-07-18","name":"GPT-4o Mini","created":1772236800,"description":"OpenAI's cost-efficient small model that delivers GPT-4 level intelligence at a fraction of the cost. Ideal for high-volume applications requiring strong reasoning. Version: 2024-07-18.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.02112,"max_completion_cost":0.01081344,"max_cost":0.029230080000000002},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":26.49977164022545,"max_completion_cost":13.56788307979543,"max_cost":36.67568395007203},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m3-preview","name":"MiniMax M3 Preview","created":1781222400,"description":"MiniMax-M3 preview is a 1.4T-parameter frontier model from MiniMax for coding, agentic workflows, and complex reasoning, served at fp8 with a 512K context window.","context_length":524288,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.17301504,"max_cost":0.30277632},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008281178637570452,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":217.0861292767269,"max_cost":379.90072623427204},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m3-1-flash","name":"MiniMax M3.1 Flash","created":1792281600,"description":"MiniMax M3.1 Flash is a frontier model for coding, agentic workflows, and complex reasoning, with a 1M-token context window, text, image, and video input, and tunable thinking depth from low to max (max by default).","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.0625e-7,"completion":8.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.0625e-8,"input_cache_write":0.0,"max_prompt_cost":0.20625000000000002,"max_completion_cost":0.1081344,"max_cost":0.2873508},"sats_pricing":{"prompt":0.00025878683242407666,"completion":0.0010351473296963066,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000025878683242407667,"input_cache_write":0.0,"max_prompt_cost":258.7868324240767,"max_completion_cost":135.6788307979543,"max_cost":360.5459555225424},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m25","name":"MiniMax M2.5","created":1770854400,"description":"MiniMax-M2.5 is a large language model optimized for coding, agentic workflows, and modern application development with enhanced reasoning capabilities.","context_length":198000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.97e-7,"completion":1.045e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.058806000000000004,"max_completion_cost":0.03424256,"max_cost":0.083316464},"sats_pricing":{"prompt":0.00037265303869067043,"completion":0.0013111866176153217,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":73.78530166075274,"max_completion_cost":42.96496308601886,"max_cost":104.53916997495571},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m27","name":"MiniMax M2.7","created":1773792000,"description":"MiniMax-M2.7 is a large language model designed for autonomous, real-world productivity with advanced agentic capabilities through multi-agent collaboration.","context_length":198000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.5625e-8,"input_cache_write":0.0,"max_prompt_cost":0.081675,"max_completion_cost":0.0540672,"max_cost":0.12222540000000001},"sats_pricing":{"prompt":0.0005175736648481533,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009488850522216145,"input_cache_write":0.0,"max_prompt_cost":102.47958563993436,"max_completion_cost":67.83941539897715,"max_cost":153.35914718916723},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mercury-2","name":"Inception: Mercury 2","created":1772636275,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":8.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.0352,"max_completion_cost":0.04125,"max_cost":0.0627},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.0010351473296963066,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0,"max_prompt_cost":44.16628606704242,"max_completion_cost":51.757366484815336,"max_cost":78.67119705691931},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":50000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inception/mercury-2-20260304","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"mercury-2-5","name":"Mercury 2.5","created":1788825600,"description":"Mercury 2.5 is a diffusion-based reasoning model from Inception with fast parallel token generation, tunable reasoning, tool calling, and structured output support.","context_length":260000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.03125e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.7500000000000005e-8,"input_cache_write":0.0,"max_prompt_cost":0.07150000000000001,"max_completion_cost":0.067584,"max_cost":0.1210616},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.0012939341621203834,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0,"max_prompt_cost":89.71276857367991,"max_completion_cost":84.79926924872144,"max_cost":151.89889935607565},"per_request_limits":null,"top_provider":{"context_length":260000,"max_completion_tokens":65536,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mercury-3","name":"Mercury 3","created":1792368000,"description":"Mercury 3 is Inception's most capable diffusion-based reasoning model, generating over 1,000 tokens per second with a 1M-token context window, tunable reasoning, tool calling, and structured output support.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1000000000000002e-7,"completion":3.85e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.11000000000000001,"max_completion_cost":0.05046272,"max_cost":0.14604480000000003},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00048306875385827644,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.0,"max_prompt_cost":138.01964395950756,"max_completion_cost":63.31678770571201,"max_cost":183.245920892159},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia-nemotron-3-nano-30b-a3b","name":"NVIDIA Nemotron 3 Nano 30B","created":1769472000,"description":"NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.00540672,"max_cost":0.014615040000000001},"sats_pricing":{"prompt":0.00010351473296963067,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.249885820112725,"max_completion_cost":6.783941539897715,"max_cost":18.337841975036014},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia-nemotron-3-5-super-vl-120b-a12b","name":"NVIDIA Nemotron 3.5 Super VL 120B","created":1792108800,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, combining reasoning, instruction following, and tool use for long-running agentic workflows.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168000000001,"max_completion_cost":0.05632,"max_cost":0.09146368},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":72.3620430922423,"max_completion_cost":70.66605770726787,"max_cost":114.76167771660302},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":102400,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia-nemotron-3-ultra-550b-a55b","name":"NVIDIA Nemotron 3 Ultra","created":1780531200,"description":"NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads.","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.875000000000001e-7,"completion":3.4375000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.0625e-7,"input_cache_write":0.0,"max_prompt_cost":0.17600000000000002,"max_completion_cost":0.11264000000000002,"max_cost":0.266112},"sats_pricing":{"prompt":0.0008626227747469223,"completion":0.004313113873734612,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00025878683242407666,"input_cache_write":0.0,"max_prompt_cost":220.8314303352121,"max_completion_cost":141.33211541453576,"max_cost":333.8971226668407},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-gemma-4-26b-a4b-uncensored-p","name":"Gemma 4 26B A4B Uncensored","created":1779580800,"description":"Gemma 4 26B A4B Uncensored running in a Trusted Execution Environment (TEE). An uncensored variant of Google's Gemma 4 MoE model with 25.2B total / 3.8B active parameters, with hardware attestation evidence available for independent verification.","context_length":64000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.0900000000000003e-7,"completion":9.68e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.013376000000000002,"max_completion_cost":0.003964928,"max_cost":0.016484864000000002},"sats_pricing":{"prompt":0.00026223732352306437,"completion":0.0012145728668436664,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":16.78318870547612,"max_completion_cost":4.974890462591658,"max_cost":20.683955090917305},"per_request_limits":null,"top_provider":{"context_length":64000,"max_completion_tokens":4096,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-glm-5-2-p","name":"GLM 5.2","created":1781568000,"description":"GLM 5.2 running in a Trusted Execution Environment (TEE). A Z.AI model for long-horizon tasks with enhanced reasoning and project-level engineering context, with hardware attestation evidence available for independent verification.","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":6.3250000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":0.0,"max_prompt_cost":1.0092544,"max_completion_cost":0.20725760000000001,"max_cost":1.1534336},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.007936129527671684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00041405893187852267,"input_cache_write":0.0,"max_prompt_cost":1266.3357541142402,"max_completion_cost":260.05109236274575,"max_cost":1447.240861844846},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-glm-5-3-p","name":"GLM 5.3","created":1788652800,"description":"GLM 5.3 running in a Trusted Execution Environment (TEE). Z.ai's flagship model with 1M context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":6.0500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.575e-7,"input_cache_write":0.0,"max_prompt_cost":1.9250000000000003,"max_completion_cost":0.19824640000000002,"max_cost":2.0601680000000004},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.007591080417772916,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00044856384286839955,"input_cache_write":0.0,"max_prompt_cost":2415.3437692913826,"max_completion_cost":248.74452312958292,"max_cost":2584.9423077888255},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-gpt-oss-120b-p","name":"GPT OSS 120B","created":1773792000,"description":"GPT OSS 120B running in a Trusted Execution Environment (TEE). OpenAI's open-weight 117B-parameter MoE model with configurable reasoning depth and native tool use, with hardware attestation evidence available for independent verification.","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.4300000000000002e-7,"completion":7.15e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.018304000000000004,"max_completion_cost":0.02342912,"max_cost":0.03704729600000001},"sats_pricing":{"prompt":0.00017942553714735983,"completion":0.0008971276857367991,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":22.96646875486206,"max_completion_cost":29.397080006223433,"max_cost":46.48413275984081},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-kimi-k3-p","name":"Kimi K3","created":1788825600,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.125e-6,"completion":0.000020625,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-7,"input_cache_write":0.0,"max_prompt_cost":4.125,"max_completion_cost":2.70336,"max_cost":6.287688},"sats_pricing":{"prompt":0.0051757366484815335,"completion":0.025878683242407666,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005175736648481533,"input_cache_write":0.0,"max_prompt_cost":5175.736648481533,"max_completion_cost":3391.9707699488577,"max_cost":7889.31326444062},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-qwen-2-5-7b-p","name":"Qwen 2.5 7B","created":1773792000,"description":"Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification.","context_length":32000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.500000000000001e-8,"completion":1.4300000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0017600000000000003,"max_completion_cost":0.0005857280000000001,"max_cost":0.0021204480000000005},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.00017942553714735983,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.2083143033521213,"max_completion_cost":0.7349270001555859,"max_cost":2.6605770726786355},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-qwen3-vl-30b-a3b-p","name":"Qwen3 VL 30B A3B","created":1773792000,"description":"Qwen3 VL 30B A3B running in a Trusted Execution Environment (TEE). A multimodal model unifying text generation with visual understanding for images, with hardware attestation evidence available for independent verification.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0352,"max_completion_cost":0.00405504,"max_cost":0.038128640000000005},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.001242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":44.16628606704242,"max_completion_cost":5.087956154923287,"max_cost":47.840921067820354},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-qwen3-6-35b-a3b","name":"Qwen 3.6 35B A3B FP8","created":1779235200,"description":"Qwen 3.6 35B A3B FP8 running in a Trusted Execution Environment (TEE). A fast mixture-of-experts model with ~3B active parameters per token. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","context_length":32000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.002e-7,"completion":1.2980000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.0064064000000000005,"max_completion_cost":0.0053166080000000004,"max_cost":0.010902988800000001},"sats_pricing":{"prompt":0.00025119575200630375,"completion":0.0016286317987221893,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008281178637570452,"input_cache_write":0.0,"max_prompt_cost":8.03826406420172,"max_completion_cost":6.670875847566087,"max_cost":13.680242111549987},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-deepseek-v4-flash","name":"DeepSeek V4 Flash","created":1783382400,"description":"DeepSeek V4 Flash running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.002e-7,"completion":4.1030000000000007e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.18e-8,"input_cache_write":0.0,"max_prompt_cost":0.20020000000000002,"max_completion_cost":0.0033611776000000006,"max_cost":0.2019211392},"sats_pricing":{"prompt":0.00025119575200630375,"completion":0.0005148132719689632,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000052447464704612865,"input_cache_write":0.0,"max_prompt_cost":251.19575200630376,"max_completion_cost":4.217350323969747,"max_cost":253.35530672983782},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":8192,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-glm-5-3-flash","name":"GLM 5.3 Flash","created":1788652800,"description":"GLM 5.3 Flash running in a Trusted Execution Environment (TEE). A fast, low-cost multimodal model with 1M context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.7600000000000001e-7,"completion":5.94e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.18e-8,"input_cache_write":0.0,"max_prompt_cost":0.17600000000000002,"max_completion_cost":0.019464192,"max_cost":0.189697024},"sats_pricing":{"prompt":0.0002208314303352121,"completion":0.0007453060773813409,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000052447464704612865,"input_cache_write":0.0,"max_prompt_cost":220.8314303352121,"max_completion_cost":24.422189543631777,"max_cost":238.0174155696196},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-qwen3-8-27b","name":"Qwen 3.8 27B","created":1788652800,"description":"Qwen 3.8 27B running in a Trusted Execution Environment (TEE). A multimodal model with 262K context supporting text and image input. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.17e-7,"completion":3.883e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.17e-8,"input_cache_write":0.0,"max_prompt_cost":0.135528448,"max_completion_cost":0.031809536,"max_cost":0.16310272},"sats_pricing":{"prompt":0.0006486923266096855,"completion":0.004872093431770617,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006486923266096855,"input_cache_write":0.0,"max_prompt_cost":170.05080126676938,"max_completion_cost":39.91218939306489,"max_cost":204.64890312024775},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":8192,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e2ee-kimi-k2-6","name":"Kimi K2.6","created":1788652800,"description":"Kimi K2.6 running in a Trusted Execution Environment (TEE). MoonshotAI's multimodal model with 262K context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":9.570000000000001e-7,"completion":4.532000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.84e-7,"input_cache_write":0.0,"max_prompt_cost":0.25087180800000003,"max_completion_cost":0.03712614400000001,"max_cost":0.280158208},"sats_pricing":{"prompt":0.0012007709024477158,"completion":0.005686409331131712,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006072864334218332,"input_cache_write":0.0,"max_prompt_cost":314.774887451254,"max_completion_cost":46.58306524063099,"max_cost":351.5212374590333},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":8192,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"hy4-preview","name":"Tencent: Hy4 preview","created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9.174e-7,"completion":2.7511000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.6200000000000003e-8,"input_cache_write":0.0,"max_prompt_cost":0.9619636224,"max_completion_cost":0.17607040000000002,"max_cost":1.0793204224},"sats_pricing":{"prompt":0.001151083830622293,"completion":0.0034518712954272842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00005796825046299317,"input_cache_write":0.0,"max_prompt_cost":1206.9988787786015,"max_completion_cost":220.91976290734618,"max_cost":1354.2492765261209},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":64000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy4-preview-20260827","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"venice-sd35","name":"Venice SD35","created":1743099022,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.011000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.044000000000000004,"max_cost":0.044000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.801964395950757,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":55.207857583803026,"max_cost":55.207857583803026},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.01,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"grok-imagine-image-2-0","name":"Grok Imagine 2.0","created":1786406400,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.11000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.44000000000000006,"max_cost":0.44000000000000006},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":138.01964395950756,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":552.0785758380302,"max_cost":552.0785758380302},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.1,"tiers":[{"resolution":"1K","quality":null,"usd":0.07},{"resolution":"2K","quality":null,"usd":0.1},{"resolution":"1K","quality":"low","usd":0.05},{"resolution":"1K","quality":"medium","usd":0.07},{"resolution":"2K","quality":"low","usd":0.07},{"resolution":"2K","quality":"medium","usd":0.1}],"default_resolution":"1K","default_quality":"medium","resolutions":["1K","2K"],"qualities":["low","medium"],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-2-turbo","name":"Krea 2 Turbo","created":1782777600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.066,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.264,"max_cost":0.264},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":82.81178637570453,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":331.2471455028181,"max_cost":331.2471455028181},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.06,"tiers":[{"resolution":"1K","quality":null,"usd":0.04},{"resolution":"2K","quality":null,"usd":0.06}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux-2-pro","name":"Flux 2 Pro","created":1764086377,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.033,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.132,"max_cost":0.132},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":41.405893187852264,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":165.62357275140906,"max_cost":165.62357275140906},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.03,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux-2-max","name":"Flux 2 Max","created":1764086377,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.099,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.396,"max_cost":0.396},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":124.2176795635568,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":496.8707182542272,"max_cost":496.8707182542272},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.09,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux-3-image","name":"Black Forest Labs: FLUX 3 Image","created":1790885807,"description":"FLUX.3 Image is Black Forest Labs' flagship image generation and editing model. It handles text-to-image and multi-reference editing with up to 10 input images, and renders at fixed resolution tiers...","context_length":46864,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.6677000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":2.6708000000000003,"max_cost":2.6708000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":837.7792388342109,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":3351.1169553368436,"max_cost":3351.1169553368436},"per_request_limits":null,"top_provider":{"context_length":46864,"max_completion_tokens":42177,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"black-forest-labs/flux-3-image-20261001","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.607,"tiers":[{"resolution":null,"quality":null,"usd":0.607}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"black-forest-labs":{"max_usd":0.607,"tiers":[{"resolution":null,"quality":null,"usd":0.607}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"black-forest-labs","parameters":{"resolution":{"type":"enum","values":["768","1K","1.5K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["21:9","2:1","16:9","3:2","7:5","4:3","5:4","1:1","4:5","3:4","5:7","2:3","9:16","1:2","9:21","auto"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":10}},"unreported_cost_usd":0.041}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-2-5-flare","name":"GPT Image 2.5 Flare","created":1788825600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.25300000000000006,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.0120000000000002,"max_cost":1.0120000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":317.44518110686744,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1269.7807244274697,"max_cost":1269.7807244274697},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.23,"tiers":[{"resolution":"1K","quality":null,"usd":0.07},{"resolution":"2K","quality":null,"usd":0.15},{"resolution":"4K","quality":null,"usd":0.23},{"resolution":"1K","quality":"high","usd":0.07},{"resolution":"1K","quality":"low","usd":0.03},{"resolution":"1K","quality":"medium","usd":0.04},{"resolution":"2K","quality":"high","usd":0.15},{"resolution":"2K","quality":"low","usd":0.04},{"resolution":"2K","quality":"medium","usd":0.05},{"resolution":"4K","quality":"high","usd":0.23},{"resolution":"4K","quality":"low","usd":0.05},{"resolution":"4K","quality":"medium","usd":0.07}],"default_resolution":"1K","default_quality":"high","resolutions":["1K","2K","4K"],"qualities":["low","medium","high"],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-2-5-sunburst","name":"GPT Image 2.5 Sunburst","created":1788825600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.25300000000000006,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.0120000000000002,"max_cost":1.0120000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":317.44518110686744,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1269.7807244274697,"max_cost":1269.7807244274697},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.23,"tiers":[{"resolution":"1K","quality":null,"usd":0.07},{"resolution":"2K","quality":null,"usd":0.15},{"resolution":"4K","quality":null,"usd":0.23},{"resolution":"1K","quality":"high","usd":0.07},{"resolution":"1K","quality":"low","usd":0.03},{"resolution":"1K","quality":"medium","usd":0.04},{"resolution":"2K","quality":"high","usd":0.15},{"resolution":"2K","quality":"low","usd":0.04},{"resolution":"2K","quality":"medium","usd":0.05},{"resolution":"4K","quality":"high","usd":0.23},{"resolution":"4K","quality":"low","usd":0.05},{"resolution":"4K","quality":"medium","usd":0.07}],"default_resolution":"1K","default_quality":"high","resolutions":["1K","2K","4K"],"qualities":["low","medium","high"],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-2","name":"GPT Image 2","created":1776729600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.924,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":3.696,"max_cost":3.696},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":1159.3650092598634,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":4637.460037039454,"max_cost":4637.460037039454},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.84,"tiers":[{"resolution":"1K","quality":null,"usd":0.27},{"resolution":"2K","quality":null,"usd":0.51},{"resolution":"4K","quality":null,"usd":0.84},{"resolution":"1K","quality":"high","usd":0.26},{"resolution":"1K","quality":"low","usd":0.02},{"resolution":"1K","quality":"medium","usd":0.07},{"resolution":"2K","quality":"high","usd":0.5},{"resolution":"2K","quality":"low","usd":0.03},{"resolution":"2K","quality":"medium","usd":0.13},{"resolution":"4K","quality":"high","usd":0.83},{"resolution":"4K","quality":"low","usd":0.05},{"resolution":"4K","quality":"medium","usd":0.21}],"default_resolution":"1K","default_quality":"high","resolutions":["1K","2K","4K"],"qualities":["low","medium","high"],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-1-5","name":"GPT Image 1.5","created":1765986864,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.28600000000000003,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.1440000000000001,"max_cost":1.1440000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":358.85107429471964,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1435.4042971788786,"max_cost":1435.4042971788786},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.26,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"hunyuan-image-v3","name":"Hunyuan Image 3.0","created":1772323200,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.099,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.396,"max_cost":0.396},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":124.2176795635568,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":496.8707182542272,"max_cost":496.8707182542272},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.09,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"ideogram-v4","name":"Ideogram V4","created":1780444800,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.066,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.264,"max_cost":0.264},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":82.81178637570453,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":331.2471455028181,"max_cost":331.2471455028181},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.06,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"ideogram-v4-5","name":"Ideogram V4.5","created":1790726400,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.28600000000000003,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.1440000000000001,"max_cost":1.1440000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":358.85107429471964,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1435.4042971788786,"max_cost":1435.4042971788786},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.26,"tiers":[{"resolution":"1K","quality":null,"usd":0.26},{"resolution":"2K","quality":null,"usd":0.26},{"resolution":"1K","quality":"high","usd":0.26},{"resolution":"1K","quality":"low","usd":0.04},{"resolution":"1K","quality":"medium","usd":0.07},{"resolution":"2K","quality":"high","usd":0.26},{"resolution":"2K","quality":"low","usd":0.04},{"resolution":"2K","quality":"medium","usd":0.07}],"default_resolution":"1K","default_quality":"high","resolutions":["1K","2K"],"qualities":["low","medium","high"],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-v2-large","name":"Krea v2 Large","created":1779408000,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.07700000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.30800000000000005,"max_cost":0.30800000000000005},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":96.6137507716553,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":386.4550030866212,"max_cost":386.4550030866212},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.07,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-v2-medium","name":"Krea v2 Medium","created":1779408000,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.17600000000000002,"max_cost":0.17600000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":220.8314303352121,"max_cost":220.8314303352121},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"luma-uni-1","name":"Luma Uni-1","created":1781654400,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"luma-uni-1-max","name":"Luma Uni-1 Max","created":1781654400,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.132,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.528,"max_cost":0.528},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":165.62357275140906,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":662.4942910056362,"max_cost":662.4942910056362},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.12,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"muse-image","name":"Muse Image","created":1788393600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.022000000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.08800000000000001,"max_cost":0.08800000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":27.603928791901513,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":110.41571516760605,"max_cost":110.41571516760605},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.02,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"nano-banana-2","name":"Nano Banana 2","created":1772064000,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.20900000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.8360000000000001,"max_cost":0.8360000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":262.2373235230644,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1048.9492940922576,"max_cost":1048.9492940922576},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.19,"tiers":[{"resolution":"1K","quality":null,"usd":0.1},{"resolution":"2K","quality":null,"usd":0.14},{"resolution":"4K","quality":null,"usd":0.19}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K","4K"],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"nano-banana-2-1","name":"Nano Banana 2.1","created":1791244800,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.20900000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.8360000000000001,"max_cost":0.8360000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":262.2373235230644,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1048.9492940922576,"max_cost":1048.9492940922576},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.19,"tiers":[{"resolution":"1K","quality":null,"usd":0.1},{"resolution":"2K","quality":null,"usd":0.14},{"resolution":"4K","quality":null,"usd":0.19}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K","4K"],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"nano-banana-pro","name":"Nano Banana Pro","created":1763653951,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.385,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.54,"max_cost":1.54},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":483.0687538582764,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1932.2750154331056,"max_cost":1932.2750154331056},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.35,"tiers":[{"resolution":"1K","quality":null,"usd":0.18},{"resolution":"2K","quality":null,"usd":0.23},{"resolution":"4K","quality":null,"usd":0.35}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K","4K"],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"nano-banana-2-lite","name":"Nano Banana 2 Lite","created":1782777600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.066,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.264,"max_cost":0.264},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":82.81178637570453,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":331.2471455028181,"max_cost":331.2471455028181},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.06,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4","name":"Recraft: Recraft V4","created":1778185437,"description":"Recraft V4 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. It delivers stronger compositional judgment,...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.17600000000000002,"max_cost":0.17600000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":220.8314303352121,"max_cost":220.8314303352121},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4-20260413","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4-pro","name":"Recraft: Recraft V4 Pro","created":1778185441,"description":"Recraft V4 Pro is an image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios, double the resolution of...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.275,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.1,"max_cost":1.1},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":345.0491098987689,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1380.1964395950756,"max_cost":1380.1964395950756},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4-pro-20260413","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.25,"tiers":[{"resolution":null,"quality":null,"usd":0.25}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.25,"tiers":[{"resolution":null,"quality":null,"usd":0.25}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.25}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-v4","name":"Seedream V4.5","created":1762383600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-v5-lite","name":"Seedream V5 Lite","created":1771804800,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-v5-pro","name":"Seedream V5 Pro","created":1783468800,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.12100000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.48400000000000004,"max_cost":0.48400000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":151.82160835545832,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":607.2864334218333,"max_cost":607.2864334218333},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.11,"tiers":[{"resolution":"1K","quality":null,"usd":0.06},{"resolution":"2K","quality":null,"usd":0.11}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2","name":"Qwen Image 2","created":1772582400,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2-pro","name":"Qwen Image 2 Pro","created":1772582400,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.11000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.44000000000000006,"max_cost":0.44000000000000006},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":138.01964395950756,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":552.0785758380302,"max_cost":552.0785758380302},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.1,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"wan-2-7-text-to-image","name":"Wan 2.7","created":1775001600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.04125,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.165,"max_cost":0.165},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":51.757366484815336,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":207.02946593926134,"max_cost":207.02946593926134},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.0375,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"wan-2-7-pro-text-to-image","name":"Wan 2.7 Pro","created":1775001600,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.10312500000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.41250000000000003,"max_cost":0.41250000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":129.39341621203835,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":517.5736648481534,"max_cost":517.5736648481534},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.09375,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"grok-imagine-image","name":"Grok Imagine","created":1775692800,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.17600000000000002,"max_cost":0.17600000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":220.8314303352121,"max_cost":220.8314303352121},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":"1K","quality":null,"usd":0.03},{"resolution":"2K","quality":null,"usd":0.04}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"lustify-sdxl","name":"Lustify SDXL","created":1738704152,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.011000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.044000000000000004,"max_cost":0.044000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.801964395950757,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":55.207857583803026,"max_cost":55.207857583803026},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.01,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"lustify-v7","name":"Lustify v7","created":1736635129,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.011000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.044000000000000004,"max_cost":0.044000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.801964395950757,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":55.207857583803026,"max_cost":55.207857583803026},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.01,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"lustify-v8","name":"Lustify v8","created":1774828800,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.011000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.044000000000000004,"max_cost":0.044000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.801964395950757,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":55.207857583803026,"max_cost":55.207857583803026},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.01,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image","name":"Qwen Image","created":1736635129,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.033,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.132,"max_cost":0.132},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":41.405893187852264,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":165.62357275140906,"max_cost":165.62357275140906},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.03,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"wai-illustrious","name":"Anime (WAI)","created":1736635129,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.011000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.044000000000000004,"max_cost":0.044000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.801964395950757,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":55.207857583803026,"max_cost":55.207857583803026},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.01,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"z-image-turbo","name":"Z-Image Turbo","created":1764758779,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.011000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.044000000000000004,"max_cost":0.044000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.801964395950757,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":55.207857583803026,"max_cost":55.207857583803026},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.01,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"chroma","name":"Chroma","created":1769731200,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.011000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.044000000000000004,"max_cost":0.044000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.801964395950757,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":55.207857583803026,"max_cost":55.207857583803026},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.01,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-3","name":"Qwen: Qwen Image 3","created":1785894548,"description":"Qwen Image 3 is a unified image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with a richer world...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0033000000000000004,"image_output":0.033,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0033000000000000004,"max_completion_cost":0.132,"max_cost":0.1353},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":4.140589318785227,"image_output":41.405893187852264,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.140589318785227,"max_completion_cost":165.62357275140906,"max_cost":169.7641620701943},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-image-3-20260805","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.03,"tiers":[{"resolution":null,"quality":null,"usd":0.03}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"alibaba":{"max_usd":0.03,"tiers":[{"resolution":null,"quality":null,"usd":0.03}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"alibaba","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","1:4","2:1","2:3","3:2","3:4","4:1","4:3","4:5","5:4","9:16","16:9"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":3},"seed":{"type":"boolean"}},"unreported_cost_usd":0.03}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-3-pro","name":"Qwen: Qwen Image 3 Pro","created":1785894548,"description":"Qwen Image 3 Pro is an image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with richer world knowledge...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0033000000000000004,"image_output":0.0825,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0033000000000000004,"max_completion_cost":0.33,"max_cost":0.33330000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":4.140589318785227,"image_output":103.51473296963067,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.140589318785227,"max_completion_cost":414.0589318785227,"max_cost":418.19952119730794},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-image-3-pro-20260805","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.075,"tiers":[{"resolution":null,"quality":null,"usd":0.075}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"alibaba":{"max_usd":0.075,"tiers":[{"resolution":null,"quality":null,"usd":0.075}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"alibaba","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","1:4","2:1","2:3","3:2","3:4","4:1","4:3","4:5","5:4","9:16","16:9"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":3},"seed":{"type":"boolean"}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2-1-turbo","name":"Qwen Image 2.1 Turbo","created":1791504000,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.022000000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.08800000000000001,"max_cost":0.08800000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":27.603928791901513,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":110.41571516760605,"max_cost":110.41571516760605},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.02,"tiers":[{"resolution":"1K","quality":null,"usd":0.02},{"resolution":"2K","quality":null,"usd":0.02}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2-1-pro","name":"Qwen Image 2.1 Pro","created":1789862400,"description":"Venice image model","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[{"resolution":"1K","quality":null,"usd":0.05},{"resolution":"2K","quality":null,"usd":0.05}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"text-embedding-bge-m3","name":"BGE-M3","created":1741924661,"description":"Venice embedding model","context_length":0,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embedding"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.02112,"max_cost":0.18612},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":207.02946593926134,"max_completion_cost":26.49977164022545,"max_cost":233.5292375794868},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-bge-en-icl","name":"BGE-EN-ICL","created":1776384000,"description":"Venice embedding model","context_length":0,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embedding"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-8,"completion":1.3750000000000002e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.013750000000000002,"max_completion_cost":0.00044000000000000007,"max_cost":0.014190000000000001},"sats_pricing":{"prompt":0.000017252455494938446,"completion":0.000017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.252455494938445,"max_completion_cost":0.5520785758380303,"max_cost":17.804534070776477},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-qwen3-8b","name":"Qwen3 Embedding 8B","created":1776384000,"description":"Venice embedding model","context_length":0,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embedding"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-8,"completion":1.3750000000000002e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.013750000000000002,"max_completion_cost":0.00044000000000000007,"max_cost":0.014190000000000001},"sats_pricing":{"prompt":0.000017252455494938446,"completion":0.000017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.252455494938445,"max_completion_cost":0.5520785758380303,"max_cost":17.804534070776477},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-qwen3-0-6b","name":"Qwen3 Embedding 0.6B","created":1776384000,"description":"Venice embedding model","context_length":0,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embedding"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-8,"completion":1.3750000000000002e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.013750000000000002,"max_completion_cost":0.00044000000000000007,"max_cost":0.014190000000000001},"sats_pricing":{"prompt":0.000017252455494938446,"completion":0.000017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.252455494938445,"max_completion_cost":0.5520785758380303,"max_cost":17.804534070776477},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-multilingual-e5-large-instruct","name":"Multilingual E5 Large Instruct","created":1776384000,"description":"Venice embedding model","context_length":0,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embedding"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-8,"completion":1.3750000000000002e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.013750000000000002,"max_completion_cost":0.00044000000000000007,"max_cost":0.014190000000000001},"sats_pricing":{"prompt":0.000017252455494938446,"completion":0.000017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.252455494938445,"max_completion_cost":0.5520785758380303,"max_cost":17.804534070776477},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-embedding-2-preview","name":"Google: Gemini Embedding 2 Preview","created":1776436465,"description":"Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It...","context_length":8192,"architecture":{"modality":"text+image+file+audio+video->embeddings","input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":0.0,"request":0.0,"image":4.95e-7,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00180224,"max_completion_cost":0.0,"max_cost":0.00180224},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0,"request":0.001,"image":0.000621088397817784,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.261313846632572,"max_completion_cost":0.0,"max_cost":2.261313846632572},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-2-preview","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-nemotron-embed-vl-1b-v2","name":"Nemotron Embed VL 1B v2","created":1776384000,"description":"Venice embedding model","context_length":0,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embedding"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-8,"completion":1.3750000000000002e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.013750000000000002,"max_completion_cost":0.00044000000000000007,"max_cost":0.014190000000000001},"sats_pricing":{"prompt":0.000017252455494938446,"completion":0.000017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.252455494938445,"max_completion_cost":0.5520785758380303,"max_cost":17.804534070776477},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"upscaler","name":"Upscaler","created":1744453050,"description":"Venice upscale model","context_length":0,"architecture":{"modality":"image->image","input_modalities":["image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.011000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.044000000000000004,"max_cost":0.044000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.801964395950757,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":55.207857583803026,"max_cost":55.207857583803026},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.01,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{"2x":0.02,"4x":0.08},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"firered-image-edit","name":"FireRed","created":1774396800,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.17600000000000002,"max_cost":0.17600000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":220.8314303352121,"max_cost":220.8314303352121},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-edit-uncensored","name":"Qwen Edit Uncensored","created":1780531200,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.17600000000000002,"max_cost":0.17600000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":220.8314303352121,"max_cost":220.8314303352121},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"grok-imagine-edit","name":"Grok Imagine","created":1769644800,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0025300000000000006,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0025300000000000006,"max_completion_cost":0.17600000000000002,"max_cost":0.17853000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":3.1744518110686744,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.1744518110686744,"max_completion_cost":220.8314303352121,"max_cost":224.00588214628078},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":"1K","quality":null,"usd":0.03},{"resolution":"2K","quality":null,"usd":0.04}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0023000000000000004,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"grok-imagine-image-2-0-edit","name":"Grok Imagine 2.0","created":1786406400,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.012650000000000003,"image_output":0.11000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.012650000000000003,"max_completion_cost":0.44000000000000006,"max_cost":0.45265000000000005},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":15.872259055343372,"image_output":138.01964395950756,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":15.872259055343372,"max_completion_cost":552.0785758380302,"max_cost":567.9508348933737},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.1,"tiers":[{"resolution":"1K","quality":null,"usd":0.07},{"resolution":"2K","quality":null,"usd":0.1},{"resolution":"1K","quality":"low","usd":0.05},{"resolution":"1K","quality":"medium","usd":0.07},{"resolution":"2K","quality":"low","usd":0.07},{"resolution":"2K","quality":"medium","usd":0.1}],"default_resolution":"1K","default_quality":"medium","resolutions":["1K","2K"],"qualities":["low","medium"],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.011500000000000002,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2-edit","name":"Qwen Image 2","created":1772582400,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2-pro-edit","name":"Qwen Image 2 Pro","created":1772582400,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.11000000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.44000000000000006,"max_cost":0.44000000000000006},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":138.01964395950756,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":552.0785758380302,"max_cost":552.0785758380302},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.1,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"wan-2-7-pro-edit","name":"Wan 2.7 Pro","created":1776902400,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.1034,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.4136,"max_cost":0.4136},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":129.7384653219371,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":518.9538612877484,"max_cost":518.9538612877484},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.094,"tiers":[],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux-2-max-edit","name":"Flux 2 Max","created":1767571200,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.037950000000000005,"image_output":0.132,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.037950000000000005,"max_completion_cost":0.528,"max_cost":0.5659500000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":47.61677716603011,"image_output":165.62357275140906,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":47.61677716603011,"max_completion_cost":662.4942910056362,"max_cost":710.1110681716664},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.12,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0345,"input_images_included":1,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux-3-image-edit","name":"Flux 3","created":1790812800,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":1.078,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":4.312,"max_cost":4.312},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":1352.592510803174,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":5410.370043212696,"max_cost":5410.370043212696},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.98,"tiers":[{"resolution":"1K","quality":null,"usd":0.12},{"resolution":"2K","quality":null,"usd":0.29},{"resolution":"4K","quality":null,"usd":0.98}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K","4K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-2-5-flare-edit","name":"GPT Image 2.5 Flare","created":1788825600,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.010626000000000002,"image_output":0.264,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.010626000000000002,"max_completion_cost":1.056,"max_cost":1.066626},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":13.33269760648843,"image_output":331.2471455028181,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.33269760648843,"max_completion_cost":1324.9885820112725,"max_cost":1338.3212796177609},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.24,"tiers":[{"resolution":"1K","quality":null,"usd":0.08},{"resolution":"2K","quality":null,"usd":0.15},{"resolution":"4K","quality":null,"usd":0.24},{"resolution":"1K","quality":"high","usd":0.08},{"resolution":"1K","quality":"low","usd":0.04},{"resolution":"1K","quality":"medium","usd":0.04},{"resolution":"2K","quality":"high","usd":0.15},{"resolution":"2K","quality":"low","usd":0.04},{"resolution":"2K","quality":"medium","usd":0.06},{"resolution":"4K","quality":"high","usd":0.24},{"resolution":"4K","quality":"low","usd":0.05},{"resolution":"4K","quality":"medium","usd":0.08}],"default_resolution":"1K","default_quality":"high","resolutions":["1K","2K","4K"],"qualities":["low","medium","high"],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.00966,"input_images_included":1,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-2-5-sunburst-edit","name":"GPT Image 2.5 Sunburst","created":1788825600,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.010626000000000002,"image_output":0.264,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.010626000000000002,"max_completion_cost":1.056,"max_cost":1.066626},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":13.33269760648843,"image_output":331.2471455028181,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.33269760648843,"max_completion_cost":1324.9885820112725,"max_cost":1338.3212796177609},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.24,"tiers":[{"resolution":"1K","quality":null,"usd":0.08},{"resolution":"2K","quality":null,"usd":0.15},{"resolution":"4K","quality":null,"usd":0.24},{"resolution":"1K","quality":"high","usd":0.08},{"resolution":"1K","quality":"low","usd":0.04},{"resolution":"1K","quality":"medium","usd":0.04},{"resolution":"2K","quality":"high","usd":0.15},{"resolution":"2K","quality":"low","usd":0.04},{"resolution":"2K","quality":"medium","usd":0.06},{"resolution":"4K","quality":"high","usd":0.24},{"resolution":"4K","quality":"low","usd":0.05},{"resolution":"4K","quality":"medium","usd":0.08}],"default_resolution":"1K","default_quality":"high","resolutions":["1K","2K","4K"],"qualities":["low","medium","high"],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.00966,"input_images_included":1,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-2-edit","name":"GPT Image 2","created":1776729600,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.010120000000000002,"image_output":0.924,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.010120000000000002,"max_completion_cost":3.696,"max_cost":3.7061200000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":12.697807244274697,"image_output":1159.3650092598634,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":12.697807244274697,"max_completion_cost":4637.460037039454,"max_cost":4650.157844283729},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.84,"tiers":[{"resolution":"1K","quality":null,"usd":0.34},{"resolution":"2K","quality":null,"usd":0.52},{"resolution":"4K","quality":null,"usd":0.84},{"resolution":"1K","quality":"high","usd":0.34},{"resolution":"1K","quality":"low","usd":0.03},{"resolution":"1K","quality":"medium","usd":0.08},{"resolution":"2K","quality":"high","usd":0.52},{"resolution":"2K","quality":"low","usd":0.03},{"resolution":"2K","quality":"medium","usd":0.14},{"resolution":"4K","quality":"high","usd":0.84},{"resolution":"4K","quality":"low","usd":0.04},{"resolution":"4K","quality":"medium","usd":0.22}],"default_resolution":"1K","default_quality":"high","resolutions":["1K","2K","4K"],"qualities":["low","medium","high"],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.009200000000000002,"input_images_included":1,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-1-5-edit","name":"GPT Image 1.5","created":1767555000,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.030866000000000008,"image_output":0.341,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.030866000000000008,"max_completion_cost":1.364,"max_cost":1.3948660000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":38.72831209503783,"image_output":427.8608962744734,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":38.72831209503783,"max_completion_cost":1711.4435850978937,"max_cost":1750.1718971929315},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.31,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.028060000000000005,"input_images_included":1,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"ideogram-v4-5-edit","name":"Ideogram V4.5","created":1790726400,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.28600000000000003,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.1440000000000001,"max_cost":1.1440000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":358.85107429471964,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1435.4042971788786,"max_cost":1435.4042971788786},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.26,"tiers":[{"resolution":"1K","quality":null,"usd":0.26},{"resolution":"2K","quality":null,"usd":0.26},{"resolution":"1K","quality":"high","usd":0.26},{"resolution":"1K","quality":"low","usd":0.04},{"resolution":"1K","quality":"medium","usd":0.07},{"resolution":"2K","quality":"high","usd":0.26},{"resolution":"2K","quality":"low","usd":0.04},{"resolution":"2K","quality":"medium","usd":0.07}],"default_resolution":"1K","default_quality":"high","resolutions":["1K","2K"],"qualities":["low","medium","high"],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"nano-banana-2-edit","name":"Nano Banana 2","created":1772064000,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.20900000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.8360000000000001,"max_cost":0.8360000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":262.2373235230644,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1048.9492940922576,"max_cost":1048.9492940922576},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.19,"tiers":[{"resolution":"1K","quality":null,"usd":0.1},{"resolution":"2K","quality":null,"usd":0.14},{"resolution":"4K","quality":null,"usd":0.19}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K","4K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"nano-banana-2-1-edit","name":"Nano Banana 2.1","created":1791244800,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.20900000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.8360000000000001,"max_cost":0.8360000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":262.2373235230644,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1048.9492940922576,"max_cost":1048.9492940922576},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.19,"tiers":[{"resolution":"1K","quality":null,"usd":0.1},{"resolution":"2K","quality":null,"usd":0.14},{"resolution":"4K","quality":null,"usd":0.19}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K","4K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"nano-banana-pro-edit","name":"Nano Banana Pro","created":1765584000,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.385,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.54,"max_cost":1.54},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":483.0687538582764,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1932.2750154331056,"max_cost":1932.2750154331056},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.35,"tiers":[{"resolution":"1K","quality":null,"usd":0.18},{"resolution":"2K","quality":null,"usd":0.23},{"resolution":"4K","quality":null,"usd":0.35}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K","4K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"nano-banana-2-lite-edit","name":"Nano Banana 2 Lite","created":1782777600,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.066,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.264,"max_cost":0.264},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":82.81178637570453,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":331.2471455028181,"max_cost":331.2471455028181},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.06,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"luma-uni-1-edit","name":"Luma Uni-1","created":1781654400,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.066,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.264,"max_cost":0.264},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":82.81178637570453,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":331.2471455028181,"max_cost":331.2471455028181},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.06,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"luma-uni-1-max-edit","name":"Luma Uni-1 Max","created":1781654400,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.14300000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.5720000000000001,"max_cost":0.5720000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":179.42553714735982,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":717.7021485894393,"max_cost":717.7021485894393},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.13,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"muse-image-edit","name":"Muse Image","created":1788393600,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.022000000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.08800000000000001,"max_cost":0.08800000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":27.603928791901513,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":110.41571516760605,"max_cost":110.41571516760605},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.02,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-v5-lite-edit","name":"Seedream V5 Lite","created":1771804800,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-v5-pro-edit","name":"Seedream V5 Pro","created":1783468800,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0037950000000000006,"image_output":0.12100000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0037950000000000006,"max_completion_cost":0.48400000000000004,"max_cost":0.48779500000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":4.761677716603011,"image_output":151.82160835545832,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.761677716603011,"max_completion_cost":607.2864334218333,"max_cost":612.0481111384363},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.11,"tiers":[{"resolution":"1K","quality":null,"usd":0.06},{"resolution":"2K","quality":null,"usd":0.11}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0034500000000000004,"input_images_included":1,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-v4-edit","name":"Seedream V4.5","created":1767484800,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-3-edit","name":"Qwen Image 3","created":1785888000,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0037950000000000006,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0037950000000000006,"max_completion_cost":0.17600000000000002,"max_cost":0.179795},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":4.761677716603011,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.761677716603011,"max_completion_cost":220.8314303352121,"max_cost":225.5931080518151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":"1K","quality":null,"usd":0.04},{"resolution":"2K","quality":null,"usd":0.04}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0034500000000000004,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-3-pro-edit","name":"Qwen Image 3 Pro","created":1784160000,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0037950000000000006,"image_output":0.099,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0037950000000000006,"max_completion_cost":0.396,"max_cost":0.399795},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":4.761677716603011,"image_output":124.2176795635568,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.761677716603011,"max_completion_cost":496.8707182542272,"max_cost":501.6323959708302},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.09,"tiers":[{"resolution":"1K","quality":null,"usd":0.05},{"resolution":"2K","quality":null,"usd":0.09}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0034500000000000004,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2-1-turbo-edit","name":"Qwen Image 2.1 Turbo","created":1791504000,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.022000000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.08800000000000001,"max_cost":0.08800000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":27.603928791901513,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":110.41571516760605,"max_cost":110.41571516760605},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.02,"tiers":[{"resolution":"1K","quality":null,"usd":0.02},{"resolution":"2K","quality":null,"usd":0.02}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2-1-pro-edit","name":"Qwen Image 2.1 Pro","created":1789862400,"description":"Venice inpaint model","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.22000000000000003,"max_cost":0.22000000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":69.00982197975378,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":276.0392879190151,"max_cost":276.0392879190151},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"venice","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.05,"tiers":[{"resolution":"1K","quality":null,"usd":0.05},{"resolution":"2K","quality":null,"usd":0.05}],"default_resolution":"1K","default_quality":null,"resolutions":["1K","2K"],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.62,"max_completion_cost":2.8160000000000003,"max_cost":6.8728},"sats_pricing":{"prompt":0.005520785758380302,"completion":0.027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0005520785758380303,"input_cache_write":0.006900982197975378,"max_prompt_cost":5796.825046299317,"max_completion_cost":3533.3028853633937,"max_cost":8623.467354590031},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-sol-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"openai/gpt-6-astra","name":"OpenAI: GPT-6 Astra","created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.55,"max_completion_cost":7.040000000000001,"max_cost":17.182000000000002},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0013801964395950756,"input_cache_write":0.017252455494938448,"max_prompt_cost":14492.062615748293,"max_completion_cost":8833.257213408484,"max_cost":21558.66838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-astra-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.1155,"max_completion_cost":0.0704,"max_cost":0.17182000000000003},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.00017252455494938445,"max_prompt_cost":144.92062615748293,"max_completion_cost":88.33257213408484,"max_cost":215.58668386475082},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-luna-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-sol-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-sol-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"grok-4.3","name":"Grok 4.3","created":1791442898,"description":"Grok 4.3 via xai","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":8.125000000000001e-7,"completion":1.6250000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3000000000000003e-7,"input_cache_write":0.0,"max_prompt_cost":0.8125000000000001,"max_completion_cost":1.6250000000000002,"max_cost":1.6250000000000002},"sats_pricing":{"prompt":0.0010194632792463625,"completion":0.002038926558492725,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00016311412467941803,"input_cache_write":0.0,"max_prompt_cost":1019.4632792463627,"max_completion_cost":2038.9265584927255,"max_cost":2038.9265584927255},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":1000000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-4.5","name":"Grok 4.5","created":1791575615,"description":"Grok 4.5 via xai","context_length":500000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":1.3e-6,"completion":3.9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9499999999999999e-7,"input_cache_write":0.0,"max_prompt_cost":0.65,"max_completion_cost":1.95,"max_cost":1.95},"sats_pricing":{"prompt":0.0016311412467941802,"completion":0.00489342374038254,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000244671187019127,"input_cache_write":0.0,"max_prompt_cost":815.5706233970901,"max_completion_cost":2446.71187019127,"max_cost":2446.71187019127},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":500000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":"grok-4.5","image_pricing":null},{"id":"grok-4.6","name":"Grok 4.6","created":1791575607,"description":"Grok 4.6 via xai","context_length":500000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":1.3e-6,"completion":3.9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.65,"max_completion_cost":1.95,"max_cost":1.95},"sats_pricing":{"prompt":0.0016311412467941802,"completion":0.00489342374038254,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00040778531169854504,"input_cache_write":0.0,"max_prompt_cost":815.5706233970901,"max_completion_cost":2446.71187019127,"max_cost":2446.71187019127},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":500000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":"grok-4.6","image_pricing":null},{"id":"grok-4.7","name":"Grok 4.7","created":1791575602,"description":"Grok 4.7 via xai","context_length":500000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":1.3e-6,"completion":3.9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.65,"max_completion_cost":1.95,"max_cost":1.95},"sats_pricing":{"prompt":0.0016311412467941802,"completion":0.00489342374038254,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00040778531169854504,"input_cache_write":0.0,"max_prompt_cost":815.5706233970901,"max_completion_cost":2446.71187019127,"max_cost":2446.71187019127},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":500000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":"grok-4.7","image_pricing":null},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-9,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.25952256,"max_cost":0.36765696000000003},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.140589318785227e-6,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":325.62919391509035,"max_cost":461.30802471304463},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20261017","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":4.9500000000000006e-8,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9800000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.05190451200000001,"max_completion_cost":0.5190449,"max_cost":0.5242353710000001},"sats_pricing":{"prompt":0.0000621088397817784,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002484353591271136,"input_cache_write":0.0,"max_prompt_cost":65.12583878301807,"max_completion_cost":651.2581117908927,"max_cost":657.7707205127305},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.689000000000001e-8,"completion":1.54e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.579e-8,"input_cache_write":0.0,"max_prompt_cost":0.08062500864000001,"max_completion_cost":1.45332572,"max_cost":1.46138825162},"sats_pricing":{"prompt":0.00009647573112769578,"completion":0.0019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000950955346881007,"input_cache_write":0.0,"max_prompt_cost":101.16213624295473,"max_completion_cost":1823.5227130144997,"max_cost":1833.6389652290877},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-20260816","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.173014875,"max_completion_cost":0.51904435,"max_cost":0.53634592},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":217.08592224726095,"max_completion_cost":651.257421692673,"max_cost":672.966117432132},"per_request_limits":null,"top_provider":{"context_length":1048575,"max_completion_tokens":943717,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"muse-spark-open-816b-a42b","name":"Muse Spark Open 816B A42B","created":1792016555,"description":"Muse Spark Open 816B A42B via Together (Meta)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":4.675e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":1.4417920000000002,"max_completion_cost":4.9020928,"max_cost":4.9020928},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.0058658348682790705,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":1809.0510773060576,"max_completion_cost":6150.773662840595,"max_cost":6150.773662840595},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia-nemotron-3.5-super-vl","name":"NVIDIA Nemotron 3.5 Super VL","created":1792029211,"description":"NVIDIA Nemotron 3.5 Super VL via Together (NVIDIA)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.1441792,"max_cost":0.1441792},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":180.90510773060575,"max_cost":180.90510773060575},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5.2","name":"GLM 5.2","created":0,"description":"GLM 5.2 via Together (Zai Org)","context_length":1048575,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.54e-6,"completion":4.84e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.8599999999999994e-7,"input_cache_write":0.0,"max_prompt_cost":1.6148055000000001,"max_completion_cost":5.075103,"max_cost":5.075103},"sats_pricing":{"prompt":0.0019322750154331058,"completion":0.0060728643342183326,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00035885107429471956,"input_cache_write":0.0,"max_prompt_cost":2026.135274307769,"max_completion_cost":6367.853719252988,"max_cost":6367.853719252988},"per_request_limits":null,"top_provider":{"context_length":1048575,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"muse-glimmer-30b","name":"Meta: Muse Glimmer 30B","created":1786302394,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.02162688,"max_cost":0.05947392},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":27.13576615959086,"max_cost":74.62335693887486},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-glimmer-30b-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"tev1-4b-experimental","name":"Tev1 4B Experimental","created":1790138057,"description":"Tev1 4B Experimental via Together (Together AI)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.6200000000000003e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0015138816000000001,"max_completion_cost":0.0,"max_cost":0.0015138816000000001},"sats_pricing":{"prompt":0.00005796825046299317,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.8995036311713602,"max_completion_cost":0.0,"max_cost":1.8995036311713602},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"inkling","name":"Thinking Machines: Inkling","created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","context_length":524288,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":4.4550000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.87e-7,"input_cache_write":0.0,"max_prompt_cost":0.5767168,"max_completion_cost":2.102131845,"max_cost":2.159803745},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.005589795580360057,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002346333947311628,"input_cache_write":0.0,"max_prompt_cost":723.620430922423,"max_completion_cost":2637.5953527531155,"max_cost":2709.9576718846456},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":471859,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thinkingmachines/inkling-20260715","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.8-flash","name":"Qwen: Qwen3.8 Flash","created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.170000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7600000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.06776422400000001,"max_cost":0.21113734400000003},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0006486923266096856,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002208314303352121,"input_cache_write":0.0,"max_prompt_cost":207.02946593926134,"max_completion_cost":85.0254006333847,"max_cost":264.9191004130552},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"image_pricing":null},{"id":"minimax-m3","name":"MiniMax: MiniMax M3","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.67584,"max_cost":0.67989504},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008281178637570452,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":847.9926924872144,"max_cost":853.0806486421377},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":512000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m3-20260531","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.7-max","name":"Qwen: Qwen3.7 Max","created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.6225000000000001e-6,"completion":4.8675e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.2450000000000003e-7,"input_cache_write":2.028125e-6,"max_prompt_cost":1.6225,"max_completion_cost":0.63799296,"max_cost":2.04782864},"sats_pricing":{"prompt":0.0020357897484027366,"completion":0.006107369245208209,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0004071579496805473,"input_cache_write":0.002544737185503421,"max_prompt_cost":2035.7897484027364,"max_completion_cost":800.5051017079304,"max_cost":2569.4598162080233},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-max-20260520","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gpt-oss-120b","name":"OpenAI: gpt-oss-120b","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.04325376,"max_cost":0.0540672},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":27.13576615959086,"max_completion_cost":54.27153231918172,"max_cost":67.83941539897715},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-120b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"qwen3.5-9b","name":"Qwen: Qwen3.5-9B","created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.87e-7,"completion":2.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.049020928,"max_completion_cost":0.064880475,"max_cost":0.06978268000000001},"sats_pricing":{"prompt":0.0002346333947311628,"completion":0.0003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":61.507736628405944,"max_completion_cost":81.40709144930665,"max_cost":87.55800589218408},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-9b-20260310","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"flux.1-kontext-pro","name":"FLUX.1 Kontext [pro]","created":0,"description":"FLUX.1 Kontext [pro] via Together (Black Forest Labs)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.17600000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.7040000000000001,"max_cost":0.7040000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":220.8314303352121,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":883.3257213408484,"max_cost":883.3257213408484},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.16,"tiers":[{"resolution":"512","quality":null,"usd":0.01},{"resolution":"1K","quality":null,"usd":0.04},{"resolution":"2K","quality":null,"usd":0.16}],"default_resolution":"1K","default_quality":null,"resolutions":["512","1K","2K"],"qualities":[],"upscale":{},"unit":"megapixel","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.04,"default_steps":28,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux.1-kontext-max","name":"FLUX.1 Kontext [max]","created":0,"description":"FLUX.1 Kontext [max] via Together (Black Forest Labs)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.35200000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.4080000000000001,"max_cost":1.4080000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":441.6628606704242,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1766.6514426816968,"max_cost":1766.6514426816968},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.32,"tiers":[{"resolution":"512","quality":null,"usd":0.02},{"resolution":"1K","quality":null,"usd":0.08},{"resolution":"2K","quality":null,"usd":0.32}],"default_resolution":"1K","default_quality":null,"resolutions":["512","1K","2K"],"qualities":[],"upscale":{},"unit":"megapixel","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.08,"default_steps":28,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux.2-dev","name":"FLUX.2 [dev]","created":1764086551,"description":"FLUX.2 [dev] via Together (Black Forest Labs)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.06776,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.27104,"max_cost":0.27104},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":85.02010067905665,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":340.0804027162266,"max_cost":340.0804027162266},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.0616,"tiers":[{"resolution":"512","quality":null,"usd":0.00385},{"resolution":"1K","quality":null,"usd":0.0154},{"resolution":"2K","quality":null,"usd":0.0616}],"default_resolution":"1K","default_quality":null,"resolutions":["512","1K","2K"],"qualities":[],"upscale":{},"unit":"megapixel","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0154,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux.2-flex","name":"FLUX.2 [flex]","created":1764090764,"description":"FLUX.2 [flex] via Together (Black Forest Labs)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.132,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.528,"max_cost":0.528},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":165.62357275140906,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":662.4942910056362,"max_cost":662.4942910056362},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.12,"tiers":[{"resolution":"512","quality":null,"usd":0.0075},{"resolution":"1K","quality":null,"usd":0.03},{"resolution":"2K","quality":null,"usd":0.12}],"default_resolution":"1K","default_quality":null,"resolutions":["512","1K","2K"],"qualities":[],"upscale":{},"unit":"megapixel","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.03,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux.2-pro","name":"FLUX.2 [pro]","created":1764070232,"description":"FLUX.2 [pro] via Together (Black Forest Labs)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.132,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.528,"max_cost":0.528},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":165.62357275140906,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":662.4942910056362,"max_cost":662.4942910056362},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.12,"tiers":[{"resolution":"512","quality":null,"usd":0.0075},{"resolution":"1K","quality":null,"usd":0.03},{"resolution":"2K","quality":null,"usd":0.12}],"default_resolution":"1K","default_quality":null,"resolutions":["512","1K","2K"],"qualities":[],"upscale":{},"unit":"megapixel","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.03,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux.2-max","name":"FLUX.2 [max]","created":0,"description":"FLUX.2 [max] via Together (Black Forest Labs)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.30800000000000005,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.2320000000000002,"max_cost":1.2320000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":386.4550030866212,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1545.8200123464849,"max_cost":1545.8200123464849},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.28,"tiers":[{"resolution":"512","quality":null,"usd":0.0175},{"resolution":"1K","quality":null,"usd":0.07},{"resolution":"2K","quality":null,"usd":0.28}],"default_resolution":"1K","default_quality":null,"resolutions":["512","1K","2K"],"qualities":[],"upscale":{},"unit":"megapixel","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.07,"default_steps":50,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux.1.1-pro","name":"FLUX.1.1 [pro]","created":0,"description":"FLUX.1.1 [pro] via Together (Black Forest Labs)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.17600000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.7040000000000001,"max_cost":0.7040000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":220.8314303352121,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":883.3257213408484,"max_cost":883.3257213408484},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.16,"tiers":[{"resolution":"512","quality":null,"usd":0.01},{"resolution":"1K","quality":null,"usd":0.04},{"resolution":"2K","quality":null,"usd":0.16}],"default_resolution":"1K","default_quality":null,"resolutions":["512","1K","2K"],"qualities":[],"upscale":{},"unit":"megapixel","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.04,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-2-1.5b-instruct","name":"Arize AI Qwen 2 1.5B Instruct","created":1745522693,"description":"Arize AI Qwen 2 1.5B Instruct via Together (Togethercomputer)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1000000000000002e-7,"completion":1.1000000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0036044800000000006,"max_completion_cost":0.0036044800000000006,"max_cost":0.0036044800000000006},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00013801964395950757,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.522627693265144,"max_completion_cost":4.522627693265144,"max_cost":4.522627693265144},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"seedream-3.0","name":"ByteDance Seedream 3.0","created":1759884740,"description":"ByteDance Seedream 3.0 via Together (ByteDance)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0198,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0792,"max_cost":0.0792},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":24.84353591271136,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":99.37414365084544,"max_cost":99.37414365084544},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.018,"tiers":[{"resolution":null,"quality":null,"usd":0.018}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-4.0","name":"ByteDance Seedream 4.0","created":1759884757,"description":"ByteDance Seedream 4.0 via Together (ByteDance)","context_length":0,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.033,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.132,"max_cost":0.132},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":41.405893187852264,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":165.62357275140906,"max_cost":165.62357275140906},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.03,"tiers":[{"resolution":null,"quality":null,"usd":0.03}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen3.6-plus","name":"Qwen: Qwen3.6 Plus","created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.575e-7,"completion":2.1450000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":4.46875e-7,"max_prompt_cost":0.35750000000000004,"max_completion_cost":0.14057472000000001,"max_cost":0.4746456},"sats_pricing":{"prompt":0.00044856384286839955,"completion":0.0026913830572103973,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0005607048035854994,"max_prompt_cost":448.5638428683996,"max_completion_cost":176.3824800373406,"max_cost":595.5492428995167},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-plus-04-02","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.7-plus","name":"Qwen: Qwen3.7 Plus","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":3.5200000000000003e-7,"completion":1.4080000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.040000000000001e-8,"input_cache_write":4.4e-7,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18454937600000001,"max_cost":0.49041203200000005},"sats_pricing":{"prompt":0.0004416628606704242,"completion":0.0017666514426816968,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008833257213408484,"input_cache_write":0.0005520785758380303,"max_prompt_cost":441.6628606704242,"max_completion_cost":231.55853789517536,"max_cost":615.3317640918057},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-plus-20260602","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"ternary-bonsai-27b","name":"Ternary Bonsai 27B","created":0,"description":"Ternary Bonsai 27B via Together (Prism Ml)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","created":1792160499,"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.2883584,"max_completion_cost":0.1441792,"max_cost":0.39649280000000003},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":361.8102154612115,"max_completion_cost":180.90510773060575,"max_cost":497.48904625916583},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"reflection/beam-1.0-501b-a23b-20261016","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"max"},"image_pricing":null},{"id":"minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","created":1792379569,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.34603008,"max_cost":0.4325376},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002070294659392613,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":434.1722585534538,"max_cost":542.7153231918172},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":524288,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m3.1-flash-20261019","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"max"},"image_pricing":null},{"id":"kimi-k3.1-pro","name":"MoonshotAI: Kimi K3.1 Pro","created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":2.3068672,"max_completion_cost":10.380898000000002,"max_cost":10.611585600000002},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":2894.481723689692,"max_completion_cost":13025.162235817857,"max_cost":13314.611512343978},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k3.1-pro-20261023","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"ripple-65b-preview","name":"Ripple 65B Preview","created":1793816203,"description":"Ripple 65B Preview via Together (Ricursive AI)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.028835840000000005,"max_completion_cost":0.08650752,"max_cost":0.08650752},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":108.54306463836345,"max_cost":108.54306463836345},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.3-70b-instruct-turbo","name":"Meta Llama 3.3 70B Instruct Turbo","created":1733466629,"description":"Meta Llama 3.3 70B Instruct Turbo via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.1439999999999998e-6,"completion":1.1439999999999998e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.14994636799999997,"max_completion_cost":0.14994636799999997,"max_cost":0.14994636799999997},"sats_pricing":{"prompt":0.0014354042971788782,"completion":0.0014354042971788782,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":188.14131203982993,"max_completion_cost":188.14131203982993,"max_cost":188.14131203982993},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-7b-instruct-v0.1","name":"Mistral (7B) Instruct v0.1","created":1695860851,"description":"Mistral (7B) Instruct v0.1 via Together (mistralai)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":2.2000000000000004e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007208960000000001,"max_completion_cost":0.007208960000000001,"max_cost":0.007208960000000001},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.045255386530288,"max_completion_cost":9.045255386530288,"max_cost":9.045255386530288},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mixtral-8x7b-instruct-v0.1","name":"Mixtral-8x7B Instruct v0.1","created":1702342468,"description":"Mixtral-8x7B Instruct v0.1 via Together (mistralai)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.02162688,"max_cost":0.02162688},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":27.13576615959086,"max_completion_cost":27.13576615959086,"max_cost":27.13576615959086},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nous-hermes-2-mixtral-8x7b-dpo","name":"Nous Hermes 2 Mixtral 8X7B Dpo","created":1705292440,"description":"Nous Hermes 2 Mixtral 8X7B Dpo via Together (Nousresearch)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.02162688,"max_cost":0.02162688},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":27.13576615959086,"max_completion_cost":27.13576615959086,"max_cost":27.13576615959086},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-coder-33b-instruct","name":"Deepseek Coder 33B Instruct","created":1707283326,"description":"Deepseek Coder 33B Instruct via Together (Deepseek)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.800000000000002e-7,"completion":8.800000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.014417920000000002,"max_completion_cost":0.014417920000000002,"max_cost":0.014417920000000002},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.0011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":18.090510773060576,"max_completion_cost":18.090510773060576,"max_cost":18.090510773060576},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3-8b-chat-hf","name":"Meta Llama 3 8B Instruct Reference","created":1713420479,"description":"Meta Llama 3 8B Instruct Reference via Together (Meta)","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":2.2000000000000004e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0018022400000000003,"max_completion_cost":0.0018022400000000003,"max_cost":0.0018022400000000003},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.261313846632572,"max_completion_cost":2.261313846632572,"max_cost":2.261313846632572},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta-llama-3-8b-instruct","name":"Meta Llama 3 8B Instruct","created":1713420479,"description":"Meta Llama 3 8B Instruct via Together (Meta)","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":2.2000000000000004e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0018022400000000003,"max_completion_cost":0.0018022400000000003,"max_cost":0.0018022400000000003},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.261313846632572,"max_completion_cost":2.261313846632572,"max_cost":2.261313846632572},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-7b-instruct-v0.3","name":"Mistral (7B) Instruct v0.3","created":1716406261,"description":"Mistral (7B) Instruct v0.3 via Together (mistralai)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":2.2000000000000004e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007208960000000001,"max_completion_cost":0.007208960000000001,"max_cost":0.007208960000000001},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.045255386530288,"max_completion_cost":9.045255386530288,"max_cost":9.045255386530288},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-2-27b-it","name":"Google: Gemma 2 27B","created":1720828800,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":7.15e-7,"completion":7.15e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00585728,"max_completion_cost":0.00146432,"max_cost":0.00585728},"sats_pricing":{"prompt":0.0008971276857367991,"completion":0.0008971276857367991,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.349270001555858,"max_completion_cost":1.8373175003889646,"max_cost":7.349270001555858},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-2-27b-it","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta-llama-3-70b-instruct-turbo","name":"Meta Llama 3 70B Instruct Turbo","created":0,"description":"Meta Llama 3 70B Instruct Turbo via Together (Meta)","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":9.68e-7,"completion":9.68e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007929856,"max_completion_cost":0.007929856,"max_cost":0.007929856},"sats_pricing":{"prompt":0.0012145728668436664,"completion":0.0012145728668436664,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.949780925183315,"max_completion_cost":9.949780925183315,"max_cost":9.949780925183315},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta-llama-3.1-8b","name":"Meta Llama 3.1 8B","created":1713420479,"description":"Meta Llama 3.1 8B via Together (Meta)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":2.2000000000000004e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0036044800000000006,"max_completion_cost":0.0036044800000000006,"max_cost":0.0036044800000000006},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.522627693265144,"max_completion_cost":4.522627693265144,"max_cost":4.522627693265144},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta-llama-3.1-70b-instruct-turbo","name":"Meta Llama 3.1 70B Instruct Turbo","created":1721603683,"description":"Meta Llama 3.1 70B Instruct Turbo via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":9.68e-7,"completion":9.68e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.126877696,"max_completion_cost":0.126877696,"max_cost":0.126877696},"sats_pricing":{"prompt":0.0012145728668436664,"completion":0.0012145728668436664,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":159.19649480293305,"max_completion_cost":159.19649480293305,"max_cost":159.19649480293305},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2-1.5b-instruct","name":"Qwen 2 Instruct (1.5B)","created":1717792561,"description":"Qwen 2 Instruct (1.5B) via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":2.2000000000000002e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0007208960000000001,"max_completion_cost":0.0007208960000000001,"max_cost":0.0007208960000000001},"sats_pricing":{"prompt":0.000027603928791901512,"completion":0.000027603928791901512,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.9045255386530288,"max_completion_cost":0.9045255386530288,"max_cost":0.9045255386530288},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2-72b","name":"Qwen 2 (72B)","created":1717792561,"description":"Qwen 2 (72B) via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2-7b","name":"Qwen 2 (7B)","created":1717792561,"description":"Qwen 2 (7B) via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2-1.5b","name":"Qwen 2 (1.5B)","created":1717792561,"description":"Qwen 2 (1.5B) via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-72b-instruct-turbo","name":"Qwen2.5 72B Instruct Turbo","created":1728633510,"description":"Qwen2.5 72B Instruct Turbo via Together (Qwen)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.17301504,"max_cost":0.17301504},"sats_pricing":{"prompt":0.0016562357275140907,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":217.0861292767269,"max_cost":217.0861292767269},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-7b-instruct-turbo","name":"Qwen2.5 7B Instruct Turbo","created":1728671048,"description":"Qwen2.5 7B Instruct Turbo via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01081344,"max_completion_cost":0.01081344,"max_cost":0.01081344},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.56788307979543,"max_completion_cost":13.56788307979543,"max_cost":13.56788307979543},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.1-nemotron-70b-instruct-hf","name":"Llama 3.1 Nemotron 70B Instruct HF","created":1731110984,"description":"Llama 3.1 Nemotron 70B Instruct HF via Together (nvidia)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":9.68e-7,"completion":9.68e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.031719424,"max_completion_cost":0.031719424,"max_cost":0.031719424},"sats_pricing":{"prompt":0.0012145728668436664,"completion":0.0012145728668436664,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":39.79912370073326,"max_completion_cost":39.79912370073326,"max_cost":39.79912370073326},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-coder-32b-instruct","name":"Qwen 2.5 Coder 32B Instruct","created":1731556615,"description":"Qwen 2.5 Coder 32B Instruct via Together (Qwen)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.800000000000002e-7,"completion":8.800000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.014417920000000002,"max_completion_cost":0.014417920000000002,"max_cost":0.014417920000000002},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.0011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":18.090510773060576,"max_completion_cost":18.090510773060576,"max_cost":18.090510773060576},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.1-405b-instruct","name":"Meta Llama 3.1 405B Instruct","created":1733522566,"description":"Meta Llama 3.1 405B Instruct via Together (Meta)","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":3.85e-6,"completion":3.85e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0157696,"max_completion_cost":0.0157696,"max_cost":0.0157696},"sats_pricing":{"prompt":0.0048306875385827645,"completion":0.0048306875385827645,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":19.786496158035003,"max_completion_cost":19.786496158035003,"max_cost":19.786496158035003},"per_request_limits":null,"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.2-1b-instruct","name":"Meta Llama 3.2 1B Instruct","created":1733523047,"description":"Meta Llama 3.2 1B Instruct via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.600000000000001e-8,"completion":6.600000000000001e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.008650752000000001,"max_completion_cost":0.008650752000000001,"max_cost":0.008650752000000001},"sats_pricing":{"prompt":0.00008281178637570453,"completion":0.00008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":10.854306463836345,"max_completion_cost":10.854306463836345,"max_cost":10.854306463836345},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.2-3b-instruct","name":"Meta Llama 3.2 3B Instruct","created":1733523405,"description":"Meta Llama 3.2 3B Instruct via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.600000000000001e-8,"completion":6.600000000000001e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.008650752000000001,"max_completion_cost":0.008650752000000001,"max_cost":0.008650752000000001},"sats_pricing":{"prompt":0.00008281178637570453,"completion":0.00008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":10.854306463836345,"max_completion_cost":10.854306463836345,"max_cost":10.854306463836345},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-72b-instruct","name":"Qwen2.5 72B Instruct","created":1733523968,"description":"Qwen2.5 72B Instruct via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.04325376,"max_cost":0.04325376},"sats_pricing":{"prompt":0.0016562357275140907,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":54.27153231918172,"max_cost":54.27153231918172},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-14b-instruct","name":"Qwen 2.5 14B Instruct","created":1733873086,"description":"Qwen 2.5 14B Instruct via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":8.800000000000002e-7,"completion":8.800000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.028835840000000005,"max_completion_cost":0.028835840000000005,"max_cost":0.028835840000000005},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.0011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":36.18102154612115,"max_cost":36.18102154612115},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2-vl-72b-instruct","name":"Qwen2-VL (72B) Instruct","created":1736448718,"description":"Qwen2-VL (72B) Instruct via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.04325376,"max_cost":0.04325376},"sats_pricing":{"prompt":0.0016562357275140907,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":54.27153231918172,"max_cost":54.27153231918172},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","created":1738048961,"description":"DeepSeek R1 Distill Llama 70B via Together (DeepSeek)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2883584,"max_completion_cost":0.2883584,"max_cost":0.2883584},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":361.8102154612115,"max_completion_cost":361.8102154612115,"max_cost":361.8102154612115},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-r1-distill-qwen-14b","name":"DeepSeek R1 Distill Qwen 14B","created":1738182549,"description":"DeepSeek R1 Distill Qwen 14B via Together (DeepSeek)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.7600000000000003e-6,"completion":1.7600000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.23068672000000004,"max_completion_cost":0.23068672000000004,"max_cost":0.23068672000000004},"sats_pricing":{"prompt":0.002208314303352121,"completion":0.002208314303352121,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":289.4481723689692,"max_completion_cost":289.4481723689692,"max_cost":289.4481723689692},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-r1-distill-qwen-1.5b","name":"DeepSeek R1 Distill Qwen 1.5B","created":1738185844,"description":"DeepSeek R1 Distill Qwen 1.5B via Together (DeepSeek)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.9800000000000005e-7,"completion":1.9800000000000005e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.025952256000000007,"max_completion_cost":0.025952256000000007,"max_cost":0.025952256000000007},"sats_pricing":{"prompt":0.00024843535912711366,"completion":0.00024843535912711366,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":32.56291939150904,"max_completion_cost":32.56291939150904,"max_cost":32.56291939150904},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":8.800000000000001e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00180224,"max_completion_cost":0.0014417920000000001,"max_cost":0.002342912},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.00011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.261313846632572,"max_completion_cost":1.8090510773060575,"max_cost":2.939708000622343},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-24b-instruct-2501","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwq-32b","name":"Qwen QwQ-32B","created":1741207789,"description":"Qwen QwQ-32B via Together (Qwen)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.17301504,"max_cost":0.17301504},"sats_pricing":{"prompt":0.0016562357275140907,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":217.0861292767269,"max_cost":217.0861292767269},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta-llama-3.1-8b-instruct-turbo","name":"Meta Llama 3.1 8B Instruct Turbo","created":1741298134,"description":"Meta Llama 3.1 8B Instruct Turbo via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.9800000000000005e-7,"completion":1.9800000000000005e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.025952256000000007,"max_completion_cost":0.025952256000000007,"max_cost":0.025952256000000007},"sats_pricing":{"prompt":0.00024843535912711366,"completion":0.00024843535912711366,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":32.56291939150904,"max_completion_cost":32.56291939150904,"max_cost":32.56291939150904},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta/llama-3.2-11b-vision-instruct","name":"nim/meta/llama-3.2-11b-vision-instruct","created":1741628472,"description":"nim/meta/llama-3.2-11b-vision-instruct via Together (Nvidia)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta/llama-3.2-90b-vision-instruct","name":"nim/meta/llama-3.2-90b-vision-instruct","created":1741634194,"description":"nim/meta/llama-3.2-90b-vision-instruct via Together (Meta)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistralai/mixtral-8x22b-instruct-v01","name":"nim/mistralai/mixtral-8x22b-instruct-v01","created":1741634368,"description":"nim/mistralai/mixtral-8x22b-instruct-v01 via Together (Mistral)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta/llama-3.3-70b-instruct","name":"nim/meta/llama-3.3-70b-instruct","created":1741806412,"description":"nim/meta/llama-3.3-70b-instruct via Together (Meta)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"nim/nvidia/llama-3.1-nemotron-70b-instruct","created":1741808060,"description":"nim/nvidia/llama-3.1-nemotron-70b-instruct via Together (NVIDIA)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta/llama-3.1-8b-instruct","name":"nim/meta/llama-3.1-8b-instruct","created":1741829400,"description":"nim/meta/llama-3.1-8b-instruct via Together (Meta)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta/llama-3.1-70b-instruct","name":"nim/meta/llama-3.1-70b-instruct","created":1741933887,"description":"nim/meta/llama-3.1-70b-instruct via Together (Llama)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nv-mistralai/mistral-nemo-12b-instruct","name":"nim/nv-mistralai/mistral-nemo-12b-instruct","created":1741933917,"description":"nim/nv-mistralai/mistral-nemo-12b-instruct via Together (NVIDIA)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistralai/mixtral-8x7b-instruct-v01","name":"nim/mistralai/mixtral-8x7b-instruct-v01","created":1741933961,"description":"nim/mistralai/mixtral-8x7b-instruct-v01 via Together (mistralai)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1","name":"nim/nvidia/llama-3.3-nemotron-super-49b-v1","created":1742324726,"description":"nim/nvidia/llama-3.3-nemotron-super-49b-v1 via Together (Nvidia)","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":0.0,"max_prompt_cost":0.11264,"max_completion_cost":0.12672,"max_cost":0.137984},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005520785758380303,"input_cache_write":0.0,"max_prompt_cost":141.33211541453574,"max_completion_cost":158.99862984135268,"max_cost":173.13184138280627},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen2.5-vl-72b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-27b-it","name":"Gemma 3 27B It","created":1743212460,"description":"Gemma 3 27B It via Together (Google)","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-2-7b-chat-hf","name":"meta-llama/Llama-2-7b-chat-hf","created":1743496513,"description":"meta-llama/Llama-2-7b-chat-hf via Together (Meta)","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-r1-distill-qwen-7b","name":"DeepSeek R1 Distill Qwen 7B","created":1743602298,"description":"DeepSeek R1 Distill Qwen 7B via Together (Deepseek)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-1b-it","name":"Gemma 3 1b it","created":1743632409,"description":"Gemma 3 1b it via Together (Google)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-4b-it","name":"Gemma 3 4b it","created":1743646985,"description":"Gemma 3 4b it via Together (Google)","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout Instruct (17Bx16E)","created":1743878170,"description":"Llama 4 Scout Instruct (17Bx16E) via Together (Meta)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.9800000000000005e-7,"completion":6.490000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.20761804800000005,"max_completion_cost":0.6805258240000002,"max_cost":0.6805258240000002},"sats_pricing":{"prompt":0.00024843535912711366,"completion":0.0008143158993610947,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":260.50335513207233,"max_completion_cost":853.8721084884593,"max_cost":853.8721084884593},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"cogito-v1-preview-llama-8b","name":"Cogito V1 Preview Llama 8B","created":1744128601,"description":"Cogito V1 Preview Llama 8B via Together (deepcogito)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"cogito-v1-preview-qwen-32b","name":"Cogito V1 Preview Qwen 32B","created":1744128685,"description":"Cogito V1 Preview Qwen 32B via Together (deepcogito)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"cogito-v1-preview-qwen-14b","name":"Cogito V1 Preview Qwen 14B","created":1744128691,"description":"Cogito V1 Preview Qwen 14B via Together (deepcogito)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"cogito-v1-preview-llama-70b","name":"Cogito V1 Preview Llama 70B","created":1744128722,"description":"Cogito V1 Preview Llama 70B via Together (deepcogito)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"cogito-v1-preview-llama-70b-turbo","name":"Cogito V1 Preview Llama 70B Turbo","created":1744154143,"description":"Cogito V1 Preview Llama 70B Turbo via Together (deepcogito)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2-72b-instruct","name":"Qwen2 72B Instruct","created":1744167438,"description":"Qwen2 72B Instruct via Together (Togethercomputer)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":9.9e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.03244032,"max_completion_cost":0.03244032,"max_cost":0.03244032},"sats_pricing":{"prompt":0.001242176795635568,"completion":0.001242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":40.703649239386294,"max_completion_cost":40.703649239386294,"max_cost":40.703649239386294},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.3-70b-instruct","name":"Meta Llama 3.3 70B Instruct","created":1744545240,"description":"Meta Llama 3.3 70B Instruct via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-32b","name":"Qwen2.5 32B","created":1744695057,"description":"Qwen2.5 32B via Together (Qwen)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-72b","name":"Qwen2.5 72B","created":1744695107,"description":"Qwen2.5 72B via Together (Qwen)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-3b-instruct","name":"Qwen2.5 3B Instruct","created":1744695138,"description":"Qwen2.5 3B Instruct via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-1.5b-instruct","name":"Qwen2.5 1.5B Instruct","created":1744695182,"description":"Qwen2.5 1.5B Instruct via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-14b","name":"Qwen2.5 14B","created":1744695237,"description":"Qwen2.5 14B via Together (Qwen)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-7b","name":"Qwen2.5 7B","created":1744695357,"description":"Qwen2.5 7B via Together (Qwen)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-1.5b","name":"Qwen2.5 1.5B","created":1744695368,"description":"Qwen2.5 1.5B via Together (Qwen)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta-llama-3.1-70b","name":"Llama 3.1 70B","created":1744695371,"description":"Llama 3.1 70B via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.2-1b","name":"Llama 3.2 1B","created":1744695381,"description":"Llama 3.2 1B via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-7b-instruct","name":"Qwen2.5 7B Instruct","created":1744695400,"description":"Qwen2.5 7B Instruct via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-32b-instruct","name":"Qwen2.5 32B Instruct","created":1744695404,"description":"Qwen2.5 32B Instruct via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.1-405b","name":"Llama 3.1 405B","created":1744844058,"description":"Llama 3.1 405B via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepcoder-14b-preview","name":"Deepcoder 14B Preview","created":1746765219,"description":"Deepcoder 14B Preview via Together (Togethercomputer)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-7b-v0.1","name":"Mistral 7B v0.1","created":1747775387,"description":"Mistral 7B v0.1 via Together (Mistralai)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"devstral-small-2505","name":"Devstral Small 2505","created":1747804209,"description":"Devstral Small 2505 via Together (Mistralai)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mixtral-8x22b-instruct-v0.1","name":"Mixtral 8X22b Instruct V0.1","created":1748320270,"description":"Mixtral 8X22b Instruct V0.1 via Together (Mistralai)","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"molmo-7b-d-0924","name":"Molmo 7B D 0924","created":1748451330,"description":"Molmo 7B D 0924 via Together (Allenai)","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-8b","name":"Qwen3 8B","created":1748452111,"description":"Qwen3 8B via Together (Qwen)","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-14b","name":"Qwen3 14B","created":1748453216,"description":"Qwen3 14B via Together (Qwen)","context_length":2048,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":2048,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-0.6b","name":"Qwen3 0.6B","created":1749059215,"description":"Qwen3 0.6B via Together (Qwen)","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-0.6b-base","name":"Qwen3 0.6B Base","created":1749059218,"description":"Qwen3 0.6B Base via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-1.7b","name":"Qwen3 1.7B","created":1749059220,"description":"Qwen3 1.7B via Together (Qwen)","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-1.7b-base","name":"Qwen3 1.7B Base","created":1749059223,"description":"Qwen3 1.7B Base via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-4b-base","name":"Qwen3 4B Base","created":1749059228,"description":"Qwen3 4B Base via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-14b-base","name":"Qwen3 14B Base","created":1749059231,"description":"Qwen3 14B Base via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3b","created":1749059233,"description":"Qwen3 30B A3b via Together (Qwen)","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-30b-a3b-base","name":"Qwen3 30B A3b Base","created":1749059236,"description":"Qwen3 30B A3b Base via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-2b-it","name":"Gemma 2B It","created":1749442258,"description":"Gemma 2B It via Together (Google)","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-2-9b-it","name":"Gemma 2 9B It","created":1749442480,"description":"Gemma 2 9B It via Together (Google)","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"bge-base-en-v1.5","name":"BAAI: bge-base-en-v1.5","created":1763431837,"description":"The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.900982197975378e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035333028853633936,"max_completion_cost":0.0,"max_cost":0.0035333028853633936},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-base-en-v1.5-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-4-scout-17b-16e","name":"Llama 4 Scout (17Bx16E)","created":1749624034,"description":"Llama 4 Scout (17Bx16E) via Together (Meta)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"magistral-small-2506","name":"Magistral Small 2506","created":1749674059,"description":"Magistral Small 2506 via Together (Mistralai)","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m1-40k","name":"Minimax M1 40K","created":1750710988,"description":"Minimax M1 40K via Together (MiniMaxAI)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m1-80k","name":"Minimax M1 80K","created":1751078602,"description":"Minimax M1 80K via Together (MiniMaxAI)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mixtral-8x7b-v0.1","name":"Mixtral 8X7b V0.1","created":1752016524,"description":"Mixtral 8X7b V0.1 via Together (mistralai)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"meta-llama-3.1-8b-instruct-awq-int4","name":"Meta Llama 3.1 8B Instruct Awq Int4","created":1752128301,"description":"Meta Llama 3.1 8B Instruct Awq Int4 via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"sarvam-m","name":"Sarvam M","created":1752174718,"description":"Sarvam M via Together (Sarvamai)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-r1-0528","name":"DeepSeek: R1 0528","created":1748455170,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-r1"},"pricing":{"prompt":5.5e-7,"completion":2.3650000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.85e-7,"input_cache_write":0.0,"max_prompt_cost":0.090112,"max_completion_cost":0.07749632000000001,"max_cost":0.14958592},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.0029674223451294124,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00048306875385827644,"input_cache_write":0.0,"max_prompt_cost":113.06569233162858,"max_completion_cost":97.23649540520059,"max_cost":187.68904927050346},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-r1-0528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"qwen3-32b","name":"Qwen3 32B","created":1752778157,"description":"Qwen3 32B via Together (Qwen)","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-coder-480b-a35b-instruct-fp8","name":"Qwen3 Coder 480B A35B Instruct Fp8","created":1753233591,"description":"Qwen3 Coder 480B A35B Instruct Fp8 via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.5767168,"max_completion_cost":0.5767168,"max_cost":0.5767168},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":723.620430922423,"max_completion_cost":723.620430922423,"max_cost":723.620430922423},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-235b-a22b-instruct-2507-fp8","name":"Qwen3 235B A22b Instruct 2507 Fp8","created":1753813799,"description":"Qwen3 235B A22b Instruct 2507 Fp8 via Together","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.5-air-fp8","name":"Glm 4.5 Air Fp8","created":1753840897,"description":"Glm 4.5 Air Fp8 via Together (Zai Org)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":1.21e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.028835840000000005,"max_completion_cost":0.15859712,"max_cost":0.15859712},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0015182160835545831,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":198.99561850366632,"max_cost":198.99561850366632},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3b Instruct","created":1754023367,"description":"Qwen3 Coder 30B A3b Instruct via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-oss-20b","name":"OpenAI: gpt-oss-20b","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.3e-8,"completion":1.4300000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.004325376,"max_completion_cost":0.016868852000000004,"max_cost":0.017301416000000003},"sats_pricing":{"prompt":0.00004140589318785226,"completion":0.00017942553714735983,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":5.4271532319181714,"max_completion_cost":21.165754064051157,"max_cost":21.708502511957526},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"qwen3-4b-instruct-2507","name":"Qwen3 4B Instruct 2507","created":1754614031,"description":"Qwen3 4B Instruct 2507 via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-8b-base","name":"Qwen3 8B Base","created":1755021131,"description":"Qwen3 8B Base via Together (Qwen)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v3.1","name":"Deepseek V3.1 NVFP4","created":1774480496,"description":"Deepseek V3.1 NVFP4 via Together (DeepSeek)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":1.87e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.08650752,"max_completion_cost":0.24510464,"max_cost":0.24510464},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.0023463339473116284,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":108.54306463836345,"max_completion_cost":307.53868314202975,"max_cost":307.53868314202975},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":9.900000000000001e-8,"completion":1.21e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.025952256000000003,"max_completion_cost":0.01982464,"max_cost":0.04415488000000001},"sats_pricing":{"prompt":0.0001242176795635568,"completion":0.0015182160835545831,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":32.562919391509034,"max_completion_cost":24.87445231295829,"max_cost":55.40218924249802},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-next-80b-a3b-instruct-2509","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3b Thinking","created":1757604143,"description":"Qwen3 Next 80B A3b Thinking via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.4325376,"max_cost":0.4325376},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":542.7153231918172,"max_cost":542.7153231918172},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.5v","name":"GLM 4.5V","created":1758063708,"description":"GLM 4.5V via Together (Zai Org)","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia-nemotron-nano-9b-v2","name":"Nvidia Nemotron Nano 9B V2","created":1758138256,"description":"Nvidia Nemotron Nano 9B V2 via Together (Nvidia)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":6.600000000000001e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.008650752000000001,"max_completion_cost":0.0360448,"max_cost":0.0360448},"sats_pricing":{"prompt":0.00008281178637570453,"completion":0.0003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":10.854306463836345,"max_completion_cost":45.22627693265144,"max_cost":45.22627693265144},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-next-80b-a3b-instruct-fp8","name":"Qwen3 Next 80B A3b Instruct Fp8","created":1758748745,"description":"Qwen3 Next 80B A3b Instruct Fp8 via Together (Qwen)","context_length":0,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":1e-6},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001254724035995523},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-270m-it","name":"Gemma 3 270M It","created":1759265684,"description":"Gemma 3 270M It via Together (Google)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"cwm","name":"Facebook CWM","created":1760032935,"description":"Facebook CWM via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-vl-8b-instruct","name":"Qwen3-VL-8B-Instruct","created":0,"description":"Qwen3-VL-8B-Instruct via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":1.9800000000000005e-7,"completion":7.480000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.051904512000000014,"max_completion_cost":0.19608371200000002,"max_cost":0.19608371200000002},"sats_pricing":{"prompt":0.00024843535912711366,"completion":0.0009385335789246515,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":65.12583878301808,"max_completion_cost":246.03094651362383,"max_cost":246.03094651362383},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.6","name":"Z.ai: GLM 4.6","created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.1115136,"max_completion_cost":0.2883584,"max_cost":0.32778240000000003},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":139.91879426039037,"max_completion_cost":361.8102154612115,"max_cost":411.276455856299},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.6","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"medgemma-27b-text-it","name":"Medgemma 27B Text It","created":1761265247,"description":"Medgemma 27B Text It via Together (Google)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-vl-32b-instruct","name":"Qwen3-VL-32B-Instruct","created":1761433877,"description":"Qwen3-VL-32B-Instruct via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.4325376,"max_cost":0.4325376},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":542.7153231918172,"max_cost":542.7153231918172},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m2","name":"MiniMax M2","created":1761687398,"description":"MiniMax M2 via Together (MiniMaxAI)","context_length":196608,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":196608,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-vl-235b-a22b-instruct-fp8","name":"Qwen3-VL-235B-A22B-Instruct-FP8","created":1762450858,"description":"Qwen3-VL-235B-A22B-Instruct-FP8 via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-1b-pt","name":"Gemma 3 1B Pt","created":1763600655,"description":"Gemma 3 1B Pt via Together (Google)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"trinity-mini","name":"Trinity Mini","created":1778882481,"description":"Trinity Mini via Together (Arcee AI)","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":4.950000000000001e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.006336000000000001,"max_completion_cost":0.02112,"max_cost":0.02112},"sats_pricing":{"prompt":0.00006210883978177841,"completion":0.00020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.949931492067637,"max_completion_cost":26.49977164022545,"max_cost":26.49977164022545},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"ministral-3-14b-instruct-2512","name":"Ministral 3 14B Instruct 2512","created":1764641096,"description":"Ministral 3 14B Instruct 2512 via Together (Mistralai)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":2.2000000000000004e-7,"completion":2.2000000000000004e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.05767168000000001,"max_completion_cost":0.05767168000000001,"max_cost":0.05767168000000001},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":72.3620430922423,"max_completion_cost":72.3620430922423,"max_cost":72.3620430922423},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"essentialai-rnj-1-instruct","name":"EssentialAI Rnj-1 Instruct","created":1764918345,"description":"EssentialAI Rnj-1 Instruct via Together (Essential AI)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia-nemotron-3-nano-30b-a3b-bf16","name":"Nvidia Nemotron 3 Nano 30B A3b Bf16","created":1765923022,"description":"Nvidia Nemotron 3 Nano 30B A3b Bf16 via Together (Nvidia)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.7","name":"Z.ai: GLM 4.7","created":1766378014,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.21e-7,"input_cache_write":0.0,"max_prompt_cost":0.13381632000000002,"max_completion_cost":0.31719424,"max_cost":0.36450304},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.0030364321671091663,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001518216083554583,"input_cache_write":0.0,"max_prompt_cost":167.90255311246847,"max_completion_cost":397.99123700733264,"max_cost":457.3507254814376},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.7-20251222","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"qwen3-coder-next-fp8","name":"Qwen3 Coder Next Fp8","created":0,"description":"Qwen3 Coder Next Fp8 via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.34603008,"max_cost":0.34603008},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":434.1722585534538,"max_cost":434.1722585534538},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2.5-fp4","name":"Kimi K2.5 Fp4","created":0,"description":"Kimi K2.5 Fp4 via Together (Togethercomputer)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.08e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.80740352,"max_cost":0.80740352},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.0038645500308662115,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":1013.0686032913922,"max_cost":1013.0686032913922},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-27b-pt","name":"Gemma 3 27B Pt","created":1770376600,"description":"Gemma 3 27B Pt via Together (Google)","context_length":0,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":1e-6},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001254724035995523},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.7-fp4","name":"GLM 4.7 FP4","created":1780365305,"description":"GLM 4.7 FP4 via Together (Zai Org)","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5-fp4","name":"GLM 5 Fp4","created":1770855351,"description":"GLM 5 Fp4 via Together (Zai Org)","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5","name":"Z.ai: GLM 5","created":1770829182,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":3.52e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.2230272,"max_completion_cost":0.46137344,"max_cost":0.54022144},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.004416628606704242,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":279.83758852078074,"max_completion_cost":578.8963447379384,"max_cost":677.8288255281134},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5-20260211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"minimax-m2.5-fp4","name":"MiniMax M2.5 FP4","created":1771122164,"description":"MiniMax M2.5 FP4 via Together (MiniMaxAI)","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.96e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.93427884,"max_cost":0.94869709},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.004968707182542272,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00041405893187852267,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":1172.2621168700157,"max_cost":1190.353041702008},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-397b-a17b-20260216","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"glm-4.7-fp8","name":"Glm 4.7 Fp8","created":1772499990,"description":"Glm 4.7 Fp8 via Together (Zai Org)","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3.5-9b-fp8","name":"Qwen3.5 9B Fp8","created":1772735269,"description":"Qwen3.5 9B Fp8 via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3.5-35b-a3b","name":"Qwen3.5 35B A3b","created":1772823883,"description":"Qwen3.5 35B A3b via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nvidia-nemotron-3-super-120b-a12b-fp8","name":"Nvidia Nemotron 3 Super 120B A12b Fp8","created":1773245220,"description":"Nvidia Nemotron 3 Super 120B A12b Fp8 via Together (Nvidia)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-ocr-2","name":"Deepseek OCR 2","created":1773431742,"description":"Deepseek OCR 2 via Together (Deepseek)","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3.5-122b-a10b-fp8","name":"Qwen3.5 122B A10b Fp8","created":1773680257,"description":"Qwen3.5 122B A10b Fp8 via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-ocr","name":"GLM OCR","created":1773697388,"description":"GLM OCR via Together (Zai Org)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-8b-lora","name":"Qwen3 8B Lora","created":1773849366,"description":"Qwen3 8B Lora via Together (Qwen)","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-30b-a3b-instruct-2507-lora","name":"Qwen3 30B A3B Instruct 2507 Lora","created":1774476587,"description":"Qwen3 30B A3B Instruct 2507 Lora via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"holo3-35b-a3b","name":"Holo3 35B A3b","created":1774986932,"description":"Holo3 35B A3b via Together (Hcompany)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-4-31b-it","name":"Google: Gemma 4 31B","created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.00720896,"max_cost":0.06127616},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":72.3620430922423,"max_completion_cost":9.045255386530288,"max_cost":76.88467078550744},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-4-31b-it-20260402","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"glm-5.1","name":"Z.ai: GLM 5.1","created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.54e-6,"completion":4.84e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.8600000000000005e-7,"input_cache_write":0.0,"max_prompt_cost":0.31223808000000003,"max_completion_cost":0.63438848,"max_cost":0.74477568},"sats_pricing":{"prompt":0.0019322750154331058,"completion":0.0060728643342183326,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00035885107429471967,"input_cache_write":0.0,"max_prompt_cost":391.7726239290931,"max_completion_cost":795.9824740146653,"max_cost":934.4879471209103},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.1-20260406","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"nvidia-nemotron-3-super-120b-a12b-bf16","name":"Nvidia Nemotron 3 Super 120B A12b Bf16","created":1775592211,"description":"Nvidia Nemotron 3 Super 120B A12b Bf16 via Together (Nvidia)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m2.7","name":"MiniMax: MiniMax M2.7","created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.067584,"max_completion_cost":0.17301504,"max_cost":0.19734528},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008281178637570452,"input_cache_write":0.0,"max_prompt_cost":84.79926924872144,"max_completion_cost":217.0861292767269,"max_cost":247.6138662062666},"per_request_limits":null,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.7-20260318","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemma-4-e4b-it","name":"Gemma 4 E4B-it","created":1776333729,"description":"Gemma 4 E4B-it via Together (Google)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4b It","created":1776343034,"description":"Gemma 4 26B A4b It via Together (Google)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2.6","name":"MoonshotAI: Kimi K2.6","created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.15e-7,"completion":3.751e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.18743296,"max_completion_cost":0.884969679,"max_cost":0.903713404},"sats_pricing":{"prompt":0.0008971276857367991,"completion":0.004706469859019208,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":235.17664004978747,"max_completion_cost":1110.3927273685426,"max_cost":1133.9109296501329},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.6-20260420","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gemma-4-e2b-it","name":"Gemma 4 E2B-it","created":1776814451,"description":"Gemma 4 E2B-it via Together (Google)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3.6-35b-a3b-fp8","name":"Qwen3.6 35B A3b Fp8","created":1776874155,"description":"Qwen3.6 35B A3b Fp8 via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nemotron-3-nano-omni-30b-a3b-reasoning-fp8","name":"Nemotron 3 Nano Omni 30B A3b Reasoning Fp8","created":1777391713,"description":"Nemotron 3 Nano Omni 30B A3b Reasoning Fp8 via Together (Nvidia)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.3-70b-instruct-fp8-lora","name":"Llama 3.3 70B Instruct FP8 Lora","created":1778108492,"description":"Llama 3.3 70B Instruct FP8 Lora via Together (Meta)","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mixtral-8x7b-instruct-v0.1-fp8-lora","name":"Mixtral 8x7B Instruct V0.1 FP8 Lora","created":1778113354,"description":"Mixtral 8x7B Instruct V0.1 FP8 Lora via Together (Mistral AI)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-270m-it-lora","name":"Gemma 3 270M It Lora","created":1778127957,"description":"Gemma 3 270M It Lora via Together (Google)","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-4-scout-17b-16e-instruct-fp8-lora","name":"Llama 4 Scout 17B 16E Instruct Fp8 Lora","created":1779220285,"description":"Llama 4 Scout 17B 16E Instruct Fp8 Lora via Together (Meta)","context_length":10485760,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":10485760,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-27b-it-lora","name":"Gemma 3 27B It Lora","created":1778887487,"description":"Gemma 3 27B It Lora via Together (Google)","context_length":0,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":1e-6},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001254724035995523},"per_request_limits":null,"top_provider":{"context_length":null,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-4-31b-it-lora","name":"Gemma 4 31B It Lora","created":1779138130,"description":"Gemma 4 31B It Lora via Together (Google)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-4-maverick-17b-128e-instruct-fp4","name":"Llama 4 Maverick 17B 128E Instruct Nvfp4","created":1780433820,"description":"Llama 4 Maverick 17B 128E Instruct Nvfp4 via Together (Meta)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.64e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.32e-7,"input_cache_write":0.0,"max_prompt_cost":0.133848,"max_completion_cost":0.4818528,"max_cost":0.4952376},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.0033124714550281814,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00016562357275140904,"input_cache_write":0.0,"max_prompt_cost":167.94230276992877,"max_completion_cost":604.5922899717436,"max_cost":621.3865202487365},"per_request_limits":null,"top_provider":{"context_length":202800,"max_completion_tokens":182520,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","none"],"default_effort":"high","supports_max_tokens":true},"image_pricing":null},{"id":"qwen3.5-35b-a3b-lora","name":"Qwen3.5 35B A3B Lora","created":0,"description":"Qwen3.5 35B A3B Lora via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","created":1781266361,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":3.85e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.9083266500000001,"max_cost":0.9256285500000001},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.0048306875385827645,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":1139.699280290293,"max_cost":1161.408390088684},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.7-code-20260612","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true},"image_pricing":null},{"id":"qwen3.5-2b-lora","name":"Qwen3.5 2B Lora","created":1782724957,"description":"Qwen3.5 2B Lora via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3.6-35b-a3b-lora","name":"Qwen3.6 35B A3B Lora","created":1782725489,"description":"Qwen3.6 35B A3B Lora via Together (Qwen)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-4-12b-it","name":"Gemma 4 12B It","created":1783909139,"description":"Gemma 4 12B It via Together (Google)","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5.2-fp8","name":"GLM 5.2 FP8","created":1785247694,"description":"GLM 5.2 FP8 via Together (Zai Org)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5.2-fp8-lora","name":"GLM 5.2 FP8 Lora","created":1785250448,"description":"GLM 5.2 FP8 Lora via Together (Zai Org)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5.3-fp8","name":"GLM 5.3 FP8","created":0,"description":"GLM 5.3 FP8 via Together (Zai Org)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5.3-fp8-lora","name":"GLM 5.3 FP8 Lora","created":0,"description":"GLM 5.3 FP8 Lora via Together (Zai Org)","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Unknown","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.0},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0,"max_cost":0.001},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":null},"enabled":true,"upstream_provider_id":"together","canonical_slug":null,"alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":6.5e-8,"completion":3.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":6.5e-9,"input_cache_write":8.125e-8,"max_prompt_cost":0.065,"max_completion_cost":0.0416,"max_cost":0.09828},"sats_pricing":{"prompt":0.000081557062339709,"completion":0.00040778531169854504,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":8.1557062339709e-6,"input_cache_write":0.00010194632792463626,"max_prompt_cost":81.557062339709,"max_completion_cost":52.19651989741376,"max_cost":123.31427825764003},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-haiku-5.5-20261007","alias_ids":["claude-haiku-5-5"],"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.3e-6,"completion":6.5000000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":6.5e-8,"input_cache_write":1.6250000000000001e-6,"max_prompt_cost":1.3,"max_completion_cost":0.8320000000000001,"max_cost":1.9656},"sats_pricing":{"prompt":0.0016311412467941802,"completion":0.0081557062339709,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.000081557062339709,"input_cache_write":0.002038926558492725,"max_prompt_cost":1631.1412467941802,"max_completion_cost":1043.9303979482754,"max_cost":2466.2855651528002},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","alias_ids":["claude-sonnet-5-5"],"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.6e-6,"completion":0.000013000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":1.3e-7,"input_cache_write":3.2500000000000002e-6,"max_prompt_cost":2.6,"max_completion_cost":1.6640000000000001,"max_cost":3.9312},"sats_pricing":{"prompt":0.0032622824935883603,"completion":0.0163114124679418,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.000163114124679418,"input_cache_write":0.00407785311698545,"max_prompt_cost":3262.2824935883605,"max_completion_cost":2087.860795896551,"max_cost":4932.5711303056005},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-opus-5.5-20260921","alias_ids":["claude-opus-5-5"],"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":6.5000000000000004e-6,"completion":0.000032500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":1.625e-7,"input_cache_write":8.125000000000001e-6,"max_prompt_cost":6.500000000000001,"max_completion_cost":4.16,"max_cost":9.828},"sats_pricing":{"prompt":0.0081557062339709,"completion":0.040778531169854505,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.00020389265584927252,"input_cache_write":0.010194632792463626,"max_prompt_cost":8155.706233970902,"max_completion_cost":5219.651989741376,"max_cost":12331.427825764002},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-fable-5.1-20260831","alias_ids":["claude-fable-5-1"],"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.2500000000000002e-6,"completion":0.000016250000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":3.25e-7,"input_cache_write":4.0625000000000005e-6,"max_prompt_cost":3.2500000000000004,"max_completion_cost":2.08,"max_cost":4.914},"sats_pricing":{"prompt":0.00407785311698545,"completion":0.020389265584927253,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.00040778531169854504,"input_cache_write":0.005097316396231813,"max_prompt_cost":4077.853116985451,"max_completion_cost":2609.825994870688,"max_cost":6165.713912882001},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-4.8-opus-20260528","alias_ids":["claude-opus-4-8"],"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.2500000000000002e-6,"completion":0.000016250000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":3.25e-7,"input_cache_write":4.0625000000000005e-6,"max_prompt_cost":3.2500000000000004,"max_completion_cost":2.08,"max_cost":4.914},"sats_pricing":{"prompt":0.00407785311698545,"completion":0.020389265584927253,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.00040778531169854504,"input_cache_write":0.005097316396231813,"max_prompt_cost":4077.853116985451,"max_completion_cost":2609.825994870688,"max_cost":6165.713912882001},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-4.7-opus-20260416","alias_ids":["claude-opus-4-7"],"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.95e-6,"completion":9.75e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":1.9499999999999999e-7,"input_cache_write":2.4375e-6,"max_prompt_cost":1.95,"max_completion_cost":1.248,"max_cost":2.9484},"sats_pricing":{"prompt":0.00244671187019127,"completion":0.01223355935095635,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.000244671187019127,"input_cache_write":0.0030583898377390876,"max_prompt_cost":2446.71187019127,"max_completion_cost":1565.895596922413,"max_cost":3699.4283477292},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","alias_ids":["claude-sonnet-4-6"],"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.2500000000000002e-6,"completion":0.000016250000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":3.25e-7,"input_cache_write":4.0625000000000005e-6,"max_prompt_cost":3.2500000000000004,"max_completion_cost":2.08,"max_cost":4.914},"sats_pricing":{"prompt":0.00407785311698545,"completion":0.020389265584927253,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.00040778531169854504,"input_cache_write":0.005097316396231813,"max_prompt_cost":4077.853116985451,"max_completion_cost":2609.825994870688,"max_cost":6165.713912882001},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-4.6-opus-20260205","alias_ids":["claude-opus-4-6"],"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"high","supports_max_tokens":true},"image_pricing":null},{"id":"claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":6.5e-7,"completion":3.2500000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":6.5e-8,"input_cache_write":8.125000000000001e-7,"max_prompt_cost":0.13,"max_completion_cost":0.20800000000000002,"max_cost":0.2964},"sats_pricing":{"prompt":0.0008155706233970901,"completion":0.00407785311698545,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.000081557062339709,"input_cache_write":0.0010194632792463625,"max_prompt_cost":163.114124679418,"max_completion_cost":260.98259948706885,"max_cost":371.9002042690731},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-4.5-haiku-20251001","alias_ids":["claude-haiku-4-5-20251001"],"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.95e-6,"completion":9.75e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.006500000000000001,"internal_reasoning":0.0,"input_cache_read":1.9499999999999999e-7,"input_cache_write":2.4375e-6,"max_prompt_cost":1.95,"max_completion_cost":0.624,"max_cost":2.4492},"sats_pricing":{"prompt":0.00244671187019127,"completion":0.01223355935095635,"request":0.001,"image":0.0,"image_output":0.0,"web_search":8.155706233970902,"internal_reasoning":0.0,"input_cache_read":0.000244671187019127,"input_cache_write":0.0030583898377390876,"max_prompt_cost":2446.71187019127,"max_completion_cost":782.9477984612065,"max_cost":3073.0701089602353},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"anthropic","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","alias_ids":["claude-sonnet-4-5-20250929"],"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"hy4","name":"Tencent: Hy4","created":1793766031,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.587e-7,"completion":1.3755500000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.3100000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.4809818112,"max_completion_cost":0.09014804480000001,"max_cost":0.5410684928},"sats_pricing":{"prompt":0.0005755419153111465,"completion":0.0017259356477136421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000028984125231496586,"input_cache_write":0.0,"max_prompt_cost":603.4994393893007,"max_completion_cost":113.11091860856125,"max_cost":678.8916430360307},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy4-20261104","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-5.3-flashx-legal","name":"Z.ai: GLM 5.3 FlashX Legal","created":1793626154,"description":"GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.0700000000000003e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.42677043200000003,"max_completion_cost":0.18022400000000002,"max_cost":0.5536481280000001},"sats_pricing":{"prompt":0.0005106726826501779,"completion":0.0017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":535.479118882593,"max_completion_cost":226.1313846632572,"max_cost":694.6756136855261},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flashx-legal-20261102","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"particle-1","name":"Particle AI: Particle-1","created":1793207893,"description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-9,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.0720896,"max_cost":0.12255232},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.140589318785227e-6,"input_cache_write":0.0,"max_prompt_cost":72.3620430922423,"max_completion_cost":90.45255386530287,"max_cost":153.76934157101488},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"particle-ai/particle-1-20261027","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"high"},"image_pricing":null},{"id":"gpt-6.1-terra-pro","name":"OpenAI: GPT-6.1 Terra Pro","created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1449.2062615748293,"max_completion_cost":883.3257213408484,"max_cost":2155.866838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-terra-pro-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-terra-pro:batch","name":"OpenAI: GPT-6.1 Terra Pro (batch)","created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":6.875000000000001e-7,"max_prompt_cost":0.5775,"max_completion_cost":0.35200000000000004,"max_cost":0.8591},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0008626227747469223,"max_prompt_cost":724.6031307874147,"max_completion_cost":441.6628606704242,"max_cost":1077.933419323754},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-terra-pro-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-terra","name":"OpenAI: GPT-6.1 Terra","created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1449.2062615748293,"max_completion_cost":883.3257213408484,"max_cost":2155.866838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-terra-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-terra:batch","name":"OpenAI: GPT-6.1 Terra (batch)","created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":6.875000000000001e-7,"max_prompt_cost":0.5775,"max_completion_cost":0.35200000000000004,"max_cost":0.8591},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0008626227747469223,"max_prompt_cost":724.6031307874147,"max_completion_cost":441.6628606704242,"max_cost":1077.933419323754},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-terra-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"glimpse","name":"Elorian: Glimpse","created":1792206629,"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.8448,"max_cost":0.84885504},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.004140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008281178637570452,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":1059.9908656090179,"max_cost":1065.0788217639413},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":256000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"elorian/glimpse-20261016","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"ternary-bonsai-2-9b","name":"PrismML: Ternary Bonsai 2 9B","created":1792130995,"description":"Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":8.800000000000001e-8,"completion":1.4300000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.023068672000000002,"max_completion_cost":0.009371648000000002,"max_cost":0.026673152000000006},"sats_pricing":{"prompt":0.00011041571516760605,"completion":0.00017942553714735983,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":28.94481723689692,"max_completion_cost":11.758832002489374,"max_cost":33.46744493016207},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"prism-ml/ternary-bonsai-2-9b-20261015","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"moondream3-preview","name":"Moondream: Moondream 3 Preview","created":1792102385,"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","context_length":32000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.011264000000000001,"max_cost":0.020472320000000002},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.249885820112725,"max_completion_cost":14.133211541453575,"max_cost":25.687111976591872},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moondream/moondream3-preview-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"moondream3.1-9b-a2b","name":"Moondream: Moondream 3.1","created":1792102373,"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","context_length":32000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.011264000000000001,"max_cost":0.020472320000000002},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.249885820112725,"max_completion_cost":14.133211541453575,"max_cost":25.687111976591872},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moondream/moondream3.1-9b-a2b-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.5190449,"max_cost":0.53634647},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":651.2581117908927,"max_cost":672.9668075303518},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-super-vl-20261015","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"pareto-26.10","name":"Pareto 26.10","created":1792073620,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":3.52e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.92274688,"max_completion_cost":0.46137344,"max_cost":1.26877696},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.004416628606704242,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":1157.7926894758768,"max_completion_cost":578.8963447379384,"max_cost":1591.9649480293306},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"unbiased/pareto-26.10-20261015","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"pareto-latest","name":"Pareto Latest","created":1791933050,"description":"This model always redirects to the latest model in the Pareto family.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":3.52e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.92274688,"max_completion_cost":0.46137344,"max_cost":1.26877696},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.004416628606704242,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":1157.7926894758768,"max_completion_cost":578.8963447379384,"max_cost":1591.9649480293306},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~unbiased/pareto-latest","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"pareto-26.9","name":"Pareto 26.9","created":1791930537,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.7208960000000001,"max_completion_cost":1.081344,"max_cost":1.4417920000000002},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":904.5255386530288,"max_completion_cost":1356.788307979543,"max_cost":1809.0510773060576},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"unbiased/pareto-26.9-20260917","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"lfm-2.5-24b-a2b","name":"LiquidAI: LFM2.5-24B-A2B","created":1791912025,"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":7.7e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.00704,"max_completion_cost":0.00630784,"max_cost":0.01289728},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.0009661375077165529,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0,"max_prompt_cost":8.833257213408483,"max_completion_cost":7.914598463214001,"max_cost":16.18252721496434},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"liquid/lfm-2.5-24b-a2b-20261012","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-4-argon:batch","name":"Google: Gemini 4 Argon (batch)","created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":1.1e-6,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":5.500000000000001e-6,"input_cache_read":5.5e-8,"input_cache_write":2.0625e-7,"max_prompt_cost":1.1534336,"max_completion_cost":5.190449000000001,"max_cost":5.305792800000001},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0013801964395950756,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.006900982197975378,"input_cache_read":0.00006900982197975378,"input_cache_write":0.00025878683242407666,"max_prompt_cost":1447.240861844846,"max_completion_cost":6512.581117908929,"max_cost":6657.305756171989},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-4-argon-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"summarize","name":"ScaleDown: Summarize","created":1791893360,"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4000000000000004e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.044000000000000004,"max_completion_cost":0.0,"max_cost":0.043824},"sats_pricing":{"prompt":0.000055207857583803025,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":55.207857583803026,"max_completion_cost":0.0,"max_cost":54.98702615346781},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":4000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"scaledown/summarize-20260928","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"extract","name":"ScaleDown: Extract","created":1791893351,"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4000000000000004e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.044000000000000004,"max_completion_cost":0.0,"max_cost":0.0044},"sats_pricing":{"prompt":0.000055207857583803025,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":55.207857583803026,"max_completion_cost":0.0,"max_cost":5.520785758380303},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"scaledown/extract-20260928","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"step-5-preview","name":"StepFun: Step 5 Preview","created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.9700000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":0.19008000000000003,"max_cost":1.21968},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.003726530386906704,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":1380.1964395950756,"max_completion_cost":238.49794476202908,"max_cost":1530.3618122230198},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-5-preview-20261008","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-haiku-5.5:batch","name":"Anthropic: Claude Haiku 5.5 (batch)","created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":6.875e-8,"max_prompt_cost":0.055,"max_completion_cost":0.0352,"max_cost":0.08316000000000001},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.0003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":6.900982197975378e-6,"input_cache_write":0.00008626227747469223,"max_prompt_cost":69.00982197975378,"max_completion_cost":44.16628606704242,"max_cost":104.34285083338771},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-haiku-5.5-20261007","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-nano-banana-2.1","name":"Google: Nano Banana 2.1","created":1791300825,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.000033,"web_search":0.015400000000000002,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.1081344,"max_completion_cost":0.4866015,"max_cost":0.4974156},"sats_pricing":{"prompt":0.0020702946593926133,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.04140589318785227,"web_search":19.32275015433106,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":135.6788307979543,"max_completion_cost":610.5505980014756,"max_cost":624.1193091991348},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-nano-banana-2.1-20261006","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"mistral-large-4-0","name":"Mistral: Mistral Large 4","created":1791294122,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":7.7e-7,"completion":2.31e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.700000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.80740352,"max_completion_cost":0.60555264,"max_cost":1.21110528},"sats_pricing":{"prompt":0.0009661375077165529,"completion":0.0028984125231496585,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000966137507716553,"input_cache_write":0.0,"max_prompt_cost":1013.0686032913922,"max_completion_cost":759.8014524685441,"max_cost":1519.6029049370882},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-4-0-20261006","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"ling-3.1-flash","name":"inclusionAI: Ling 3.1 Flash","created":1790950024,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":2.475e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.0825,"max_completion_cost":0.06488064,"max_cost":0.12575376},"sats_pricing":{"prompt":0.00010351473296963067,"completion":0.000310544198908892,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002070294659392613,"input_cache_write":0.0,"max_prompt_cost":103.51473296963067,"max_completion_cost":81.40729847877259,"max_cost":157.78626528881236},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.1-flash-20261002","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-sol-pro-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-sol-pro:batch","name":"OpenAI: GPT-6.1 Sol Pro (batch)","created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1449.2062615748293,"max_completion_cost":883.3257213408484,"max_cost":2155.866838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-sol-pro-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","created":1791409264,"description":"GPT-6.1 Sol via openai-codex","context_length":922000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":1.3e-6,"completion":6.5000000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.500000000000001e-8,"input_cache_write":1.6250000000000001e-6,"max_prompt_cost":1.1986,"max_completion_cost":0.8320000000000001,"max_cost":1.8642},"sats_pricing":{"prompt":0.0016311412467941802,"completion":0.0081557062339709,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008155706233970902,"input_cache_write":0.002038926558492725,"max_prompt_cost":1503.9122295442342,"max_completion_cost":1043.9303979482754,"max_cost":2339.056547902854},"per_request_limits":null,"top_provider":{"context_length":922000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":"openai/gpt-6.1-sol","image_pricing":null},{"id":"gpt-6.1-sol:batch","name":"OpenAI: GPT-6.1 Sol (batch)","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1449.2062615748293,"max_completion_cost":883.3257213408484,"max_cost":2155.866838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6.1-sol-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-sonnet-5.5:batch","name":"Anthropic: Claude Sonnet 5.5 (batch)","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.1,"max_completion_cost":0.7040000000000001,"max_cost":1.6632000000000002},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1380.1964395950756,"max_completion_cost":883.3257213408484,"max_cost":2086.8570166677546},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"perceptron-mk1.5","name":"Perceptron: Perceptron Mk1.5","created":1790352661,"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","context_length":36864,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.006082560000000001,"max_completion_cost":0.0135168,"max_cost":0.018247680000000002},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.63193423238493,"max_completion_cost":16.959853849744288,"max_cost":22.895802697154792},"per_request_limits":null,"top_provider":{"context_length":36864,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perceptron/perceptron-mk1.5-20260925","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"high"},"image_pricing":null},{"id":"ember-1","name":"Fireworks: Ember-1","created":1790208461,"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-7,"input_cache_write":0.0,"max_prompt_cost":3.4603008,"max_completion_cost":15.571347000000001,"max_cost":15.9173784},"sats_pricing":{"prompt":0.004140589318785227,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00041405893187852267,"input_cache_write":0.0,"max_prompt_cost":4341.722585534538,"max_completion_cost":19537.743353726783,"max_cost":19971.917268515965},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"fireworks/ember-1-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"glm-5.3-prime","name":"Z.ai: GLM 5.3 Prime","created":1790199651,"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.08e-6,"completion":9.68e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.160000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":3.08,"max_completion_cost":1.26877696,"max_cost":3.9450752},"sats_pricing":{"prompt":0.0038645500308662115,"completion":0.012145728668436665,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0007729100061732424,"input_cache_write":0.0,"max_prompt_cost":3864.5500308662113,"max_completion_cost":1591.9649480293306,"max_cost":4949.980677249845},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-prime-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"qwen3.8-max-prime","name":"Qwen: Qwen3.8 Max Prime","created":1790191228,"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.0000132,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":4.4,"max_completion_cost":1.7301504,"max_cost":5.5534336},"sats_pricing":{"prompt":0.005520785758380302,"completion":0.016562357275140906,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":5520.7857583803025,"max_completion_cost":2170.861292767269,"max_cost":6968.026620225148},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-max-prime-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"},"image_pricing":null},{"id":"aion-3.5-mini","name":"AionLabs: Aion 3.5 Mini","created":1790170962,"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.7e-7,"completion":1.54e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9800000000000003e-7,"input_cache_write":0.0,"max_prompt_cost":0.20185088,"max_completion_cost":0.05046272,"max_cost":0.22708224},"sats_pricing":{"prompt":0.0009661375077165529,"completion":0.0019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002484353591271136,"input_cache_write":0.0,"max_prompt_cost":253.26715082284804,"max_completion_cost":63.31678770571201,"max_cost":284.92554467570403},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.5-mini-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","high","low"],"default_effort":"high"},"image_pricing":null},{"id":"aion-3.5","name":"AionLabs: Aion 3.5","created":1790170961,"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.8650752,"max_completion_cost":0.2162688,"max_cost":0.9732096000000001},"sats_pricing":{"prompt":0.004140589318785227,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0010351473296963066,"input_cache_write":0.0,"max_prompt_cost":1085.4306463836344,"max_completion_cost":271.3576615959086,"max_cost":1221.1094771815888},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.5-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","high","low"],"default_effort":"high"},"image_pricing":null},{"id":"solar-mini4","name":"Upstage: Solar Mini 4","created":1790160358,"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.02883584,"max_cost":0.05046272},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.900982197975378e-6,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":36.18102154612115,"max_cost":63.31678770571201},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"upstage/solar-mini4-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"command-a-plus","name":"Cohere: Command A+","created":1790102896,"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","context_length":192000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.06336,"max_completion_cost":0.1056,"max_cost":0.14784},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":79.49931492067634,"max_completion_cost":132.49885820112723,"max_cost":185.49840148157816},"per_request_limits":null,"top_provider":{"context_length":192000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-a-plus-05-2026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.1155,"max_completion_cost":0.0704,"max_cost":0.17182000000000003},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.00017252455494938445,"max_prompt_cost":144.92062615748293,"max_completion_cost":88.33257213408484,"max_cost":215.58668386475082},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-luna-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-luna-pro:batch","name":"OpenAI: GPT-6 Luna Pro (batch)","created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":6.875e-8,"max_prompt_cost":0.05775,"max_completion_cost":0.0352,"max_cost":0.08591000000000001},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.0003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":6.900982197975378e-6,"input_cache_write":0.00008626227747469223,"max_prompt_cost":72.46031307874146,"max_completion_cost":44.16628606704242,"max_cost":107.79334193237541},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-luna-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-luna","name":"GPT-6 Luna","created":1791409245,"description":"GPT-6 Luna via openai-codex","context_length":922000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":6.500000000000001e-8,"completion":3.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.5e-9,"input_cache_write":8.125e-8,"max_prompt_cost":0.05993000000000001,"max_completion_cost":0.0416,"max_cost":0.09321000000000002},"sats_pricing":{"prompt":0.00008155706233970902,"completion":0.00040778531169854504,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.1557062339709e-6,"input_cache_write":0.00010194632792463626,"max_prompt_cost":75.19561147721171,"max_completion_cost":52.19651989741376,"max_cost":116.95282739514273},"per_request_limits":null,"top_provider":{"context_length":922000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":"openai/gpt-6-luna","image_pricing":null},{"id":"gpt-6-luna:batch","name":"OpenAI: GPT-6 Luna (batch)","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":6.875e-8,"max_prompt_cost":0.05775,"max_completion_cost":0.0352,"max_cost":0.08591000000000001},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.0003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":6.900982197975378e-6,"input_cache_write":0.00008626227747469223,"max_prompt_cost":72.46031307874146,"max_completion_cost":44.16628606704242,"max_cost":107.79334193237541},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-luna-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-sol-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-sol-pro:batch","name":"OpenAI: GPT-6 Sol Pro (batch)","created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1449.2062615748293,"max_completion_cost":883.3257213408484,"max_cost":2155.866838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-sol-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-sol","name":"GPT-6 Sol","created":1791409253,"description":"GPT-6 Sol via openai-codex","context_length":922000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":1.3e-6,"completion":6.5000000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3000000000000003e-7,"input_cache_write":1.6250000000000001e-6,"max_prompt_cost":1.1986,"max_completion_cost":0.8320000000000001,"max_cost":1.8642},"sats_pricing":{"prompt":0.0016311412467941802,"completion":0.0081557062339709,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00016311412467941803,"input_cache_write":0.002038926558492725,"max_prompt_cost":1503.9122295442342,"max_completion_cost":1043.9303979482754,"max_cost":2339.056547902854},"per_request_limits":null,"top_provider":{"context_length":922000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":"openai/gpt-6-sol","image_pricing":null},{"id":"gpt-6-sol:batch","name":"OpenAI: GPT-6 Sol (batch)","created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1449.2062615748293,"max_completion_cost":883.3257213408484,"max_cost":2155.866838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-sol-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-opus-5.5:batch","name":"Anthropic: Claude Opus 5.5 (batch)","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.4080000000000001,"max_cost":3.3264000000000005},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.003450491098987689,"max_prompt_cost":2760.3928791901512,"max_completion_cost":1766.6514426816968,"max_cost":4173.714033335509},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5.5-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"mimo-v2.6-pro-ultraspeed","name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","created":1790021267,"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","context_length":1048576,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.785e-6,"completion":9.57e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.9600000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":5.01743616,"max_completion_cost":1.25435904,"max_cost":5.644615679999999},"sats_pricing":{"prompt":0.006003854512238578,"completion":0.012007709024477157,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004968707182542272,"input_cache_write":0.0,"max_prompt_cost":6295.497749025079,"max_completion_cost":1573.8744372562699,"max_cost":7082.434967653214},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-pro-ultraspeed-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5400000000000003e-7,"completion":3.0800000000000006e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.08e-9,"input_cache_write":0.0,"max_prompt_cost":0.16148070400000003,"max_completion_cost":0.04037017600000001,"max_cost":0.18166579200000002},"sats_pricing":{"prompt":0.0001932275015433106,"completion":0.0003864550030866212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.864550030866211e-6,"input_cache_write":0.0,"max_prompt_cost":202.61372065827845,"max_completion_cost":50.65343016456961,"max_cost":227.94043574056326},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-flash-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","created":1790021259,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.785000000000001e-7,"completion":9.570000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.96e-9,"input_cache_write":0.0,"max_prompt_cost":0.5017436160000001,"max_completion_cost":0.12543590400000001,"max_cost":0.564461568},"sats_pricing":{"prompt":0.0006003854512238579,"completion":0.0012007709024477158,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.968707182542273e-6,"input_cache_write":0.0,"max_prompt_cost":629.549774902508,"max_completion_cost":157.387443725627,"max_cost":708.2434967653214},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-pro-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"grok-4.7:batch","name":"SpaceXAI: Grok 4.7 (batch)","created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.76e-6,"completion":5.28e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":0.0,"max_prompt_cost":0.88,"max_completion_cost":2.3760000000000003,"max_cost":2.4640000000000004},"sats_pricing":{"prompt":0.002208314303352121,"completion":0.006624942910056363,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.0005520785758380303,"input_cache_write":0.0,"max_prompt_cost":1104.1571516760605,"max_completion_cost":2981.2243095253634,"max_cost":3091.6400246929697},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.7-20260916","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.8-omni-flash","name":"Qwen: Qwen3.8 Omni Flash","created":1789959954,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","context_length":1000000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","audio","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":5.170000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7600000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.06776422400000001,"max_cost":0.21113734400000003},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0006486923266096856,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002208314303352121,"input_cache_write":0.0,"max_prompt_cost":207.02946593926134,"max_completion_cost":85.0254006333847,"max_cost":264.9191004130552},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-omni-flash-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"image_pricing":null},{"id":"ternary-bonsai-2-27b","name":"PrismML: Ternary Bonsai 2 27B","created":1789754046,"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.0180224,"max_cost":0.03694592},"sats_pricing":{"prompt":0.00010351473296963067,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000051757366484815334,"input_cache_write":0.0,"max_prompt_cost":27.13576615959086,"max_completion_cost":22.61313846632572,"max_cost":46.35693385596772},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"prism-ml/ternary-bonsai-2-27b-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","none"],"default_effort":"xhigh"},"image_pricing":null},{"id":"glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","created":1789744020,"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.0700000000000003e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.42677043200000003,"max_completion_cost":0.18022400000000002,"max_cost":0.5536481280000001},"sats_pricing":{"prompt":0.0005106726826501779,"completion":0.0017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":535.479118882593,"max_completion_cost":226.1313846632572,"max_cost":694.6756136855261},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flashx-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"deepseek-pro-latest","name":"DeepSeek: DeepSeek Pro Latest","created":1789399174,"description":"This model always redirects to the latest model in the DeepSeek Pro family.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.0197e-7,"completion":8.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.0197e-7,"input_cache_write":0.0,"max_prompt_cost":0.10692329472,"max_completion_cost":3.4603008,"max_cost":3.5271278592},"sats_pricing":{"prompt":0.00012794420995046352,"completion":0.011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00012794420995046352,"input_cache_write":0.0,"max_prompt_cost":134.15922789301723,"max_completion_cost":4341.722585534538,"max_cost":4425.572102967673},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-pro-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"deepseek-flash-latest","name":"DeepSeek: DeepSeek Flash Latest","created":1789399150,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":6.6e-9,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.0069206016,"max_completion_cost":0.5190449,"max_cost":0.5197369628},"sats_pricing":{"prompt":8.281178637570454e-6,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.900982197975378e-6,"input_cache_write":0.0,"max_prompt_cost":8.683445171069076,"max_completion_cost":651.2581117908927,"max_cost":652.1264596204711},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"schematron-v2-turbo","name":"Inference.net: Schematron V2 Turbo","created":1789176949,"description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.0042239999999999995,"max_completion_cost":0.00135168,"max_cost":0.005305344},"sats_pricing":{"prompt":0.00004140589318785226,"completion":0.00020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":5.299954328045089,"max_completion_cost":1.6959853849744289,"max_cost":6.6567426360246325},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inference-net/schematron-v2-turbo-20260902","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"schematron-v2-small","name":"Inference.net: Schematron V2 Small","created":1789176933,"description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.53e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.00704,"max_completion_cost":0.002072576,"max_cost":0.008662016},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.00031744518110686737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":8.833257213408483,"max_completion_cost":2.6005109236274575,"max_cost":10.868439675377797},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inference-net/schematron-v2-small-20260902","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-astra-latest","name":"OpenAI: GPT Astra Latest","created":1789130932,"description":"This model always redirects to the latest model in the GPT Astra family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.55,"max_completion_cost":7.040000000000001,"max_cost":17.182000000000002},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0013801964395950756,"input_cache_write":0.017252455494938448,"max_prompt_cost":14492.062615748293,"max_completion_cost":8833.257213408484,"max_cost":21558.66838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-astra-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-sol-latest","name":"OpenAI: GPT Sol Latest","created":1789130928,"description":"This model always redirects to the latest model in the GPT Sol family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-sol-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-terra-latest","name":"OpenAI: GPT Terra Latest","created":1789130925,"description":"This model always redirects to the latest model in the GPT Terra family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.155,"max_completion_cost":0.7040000000000001,"max_cost":1.7182},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1449.2062615748293,"max_completion_cost":883.3257213408484,"max_cost":2155.866838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-terra-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-luna-latest","name":"OpenAI: GPT Luna Latest","created":1789130922,"description":"This model always redirects to the latest model in the GPT Luna family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.1155,"max_completion_cost":0.0704,"max_cost":0.17182000000000003},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.00017252455494938445,"max_prompt_cost":144.92062615748293,"max_completion_cost":88.33257213408484,"max_cost":215.58668386475082},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-luna-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"fugu-ultra-v2","name":"Sakana: Fugu Ultra v2","created":1789105383,"description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":5.500000000000001,"max_completion_cost":4.224,"max_cost":9.02},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.04140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":6900.982197975379,"max_completion_cost":5299.95432804509,"max_cost":11317.610804679618},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-ultra-v2-20260911","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"xhigh"},"image_pricing":null},{"id":"fugu-max","name":"Sakana: Fugu Max","created":1789104771,"description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.2,"max_completion_cost":0.8448,"max_cost":2.7632000000000003},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":2760.3928791901512,"max_completion_cost":1059.9908656090179,"max_cost":3467.05345626283},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-max-20260911","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"high"},"image_pricing":null},{"id":"ling-3.0-flash-vl","name":"inclusionAI: Ling 3.0 Flash VL","created":1789056114,"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","context_length":131072,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":1.9800000000000003e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.32e-8,"input_cache_write":0.0,"max_prompt_cost":0.008650752,"max_completion_cost":0.006488064000000001,"max_cost":0.012976128},"sats_pricing":{"prompt":0.00008281178637570452,"completion":0.0002484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000016562357275140907,"input_cache_write":0.0,"max_prompt_cost":10.854306463836343,"max_completion_cost":8.140729847877259,"max_cost":16.281459695754517},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-flash-vl-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"deepseek-v4.1-flash:batch","name":"DeepSeek: DeepSeek V4.1 Flash (batch)","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.2320000000000002e-7,"completion":3.6960000000000003e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.6960000000000005e-9,"input_cache_write":0.0,"max_prompt_cost":0.12918456320000002,"max_completion_cost":0.048444211200000004,"max_cost":0.16148070400000003},"sats_pricing":{"prompt":0.00015458200123464848,"completion":0.00046374600370394537,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.637460037039454e-6,"input_cache_write":0.0,"max_prompt_cost":162.09097652662277,"max_completion_cost":60.78411619748353,"max_cost":202.61372065827845},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"mercury-2.5","name":"Inception: Mercury 2.5","created":1788892137,"description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","context_length":260000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4000000000000004e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000005e-9,"input_cache_write":0.0,"max_prompt_cost":0.01144,"max_completion_cost":0.01081344,"max_cost":0.019369856},"sats_pricing":{"prompt":0.000055207857583803025,"completion":0.00020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5207857583803025e-6,"input_cache_write":0.0,"max_prompt_cost":14.354042971788786,"max_completion_cost":13.56788307979543,"max_cost":24.3038238969721},"per_request_limits":null,"top_provider":{"context_length":260000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inception/mercury-2.5-20260908","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"nex-n2.5-mini","name":"Nex AGI: Nex-N2.5-Mini","created":1788890061,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.75e-8,"completion":1.1e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.7500000000000002e-9,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.02595219,"max_cost":0.0266731025},"sats_pricing":{"prompt":0.00003450491098987689,"completion":0.00013801964395950757,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.450491098987689e-6,"input_cache_write":0.0,"max_prompt_cost":9.045255386530288,"max_completion_cost":32.562836579722656,"max_cost":33.46738282132228},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nex-agi/nex-n2.5-mini-20260908","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","none"],"default_effort":"high"},"image_pricing":null},{"id":"nex-n2.5-pro","name":"Nex AGI: Nex-N2.5-Pro","created":1788890050,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.064880475,"max_cost":0.0670432125},"sats_pricing":{"prompt":0.00010351473296963067,"completion":0.0003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002070294659392613,"input_cache_write":0.0,"max_prompt_cost":27.13576615959086,"max_completion_cost":81.40709144930665,"max_cost":84.12073017410552},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nex-agi/nex-n2.5-pro-20260907","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","none"],"default_effort":"high"},"image_pricing":null},{"id":"gpt-6-astra","name":"GPT-6 Astra","created":1791409219,"description":"GPT-6 Astra via openai-codex","context_length":922000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":6.5000000000000004e-6,"completion":0.000032500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.5e-7,"input_cache_write":8.125000000000001e-6,"max_prompt_cost":5.993,"max_completion_cost":4.16,"max_cost":9.321000000000002},"sats_pricing":{"prompt":0.0081557062339709,"completion":0.040778531169854505,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0008155706233970901,"input_cache_write":0.010194632792463626,"max_prompt_cost":7519.5611477211705,"max_completion_cost":5219.651989741376,"max_cost":11695.282739514274},"per_request_limits":null,"top_provider":{"context_length":922000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":"openai/gpt-6-astra","image_pricing":null},{"id":"gpt-6-astra:batch","name":"OpenAI: GPT-6 Astra (batch)","created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.775,"max_completion_cost":3.5200000000000005,"max_cost":8.591000000000001},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.008626227747469224,"max_prompt_cost":7246.0313078741465,"max_completion_cost":4416.628606704242,"max_cost":10779.33419323754},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-astra-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro","created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-6,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.55,"max_completion_cost":7.040000000000001,"max_cost":17.182000000000002},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0013801964395950756,"input_cache_write":0.017252455494938448,"max_prompt_cost":14492.062615748293,"max_completion_cost":8833.257213408484,"max_cost":21558.66838647508},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-astra-pro-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-astra-pro:batch","name":"OpenAI: GPT-6 Astra Pro (batch)","created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.775,"max_completion_cost":3.5200000000000005,"max_cost":8.591000000000001},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.008626227747469224,"max_prompt_cost":7246.0313078741465,"max_completion_cost":4416.628606704242,"max_cost":10779.33419323754},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-6-astra-pro-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"qwen3.8-max-0902","name":"Qwen: Qwen3.8 Max (0902)","created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.2,"max_completion_cost":0.8650752,"max_cost":2.7767168},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":2760.3928791901512,"max_completion_cost":1085.4306463836344,"max_cost":3484.013310112574},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-max-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"},"image_pricing":null},{"id":"muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":2.2000000000000003e-9,"input_cache_write":0.0,"max_prompt_cost":0.11534336,"max_completion_cost":0.20761796000000002,"max_cost":0.21915234000000003},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":3.450491098987689,"internal_reasoning":0.0,"input_cache_read":2.7603928791901512e-6,"input_cache_write":0.0,"max_prompt_cost":144.7240861844846,"max_completion_cost":260.50324471635713,"max_cost":274.97570854266314},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.3-contributor-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"muse-spark-1.3","name":"Meta: Muse Spark 1.3","created":1788378359,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":4.675e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":1.4417920000000002,"max_completion_cost":4.41188165,"max_cost":4.5560614},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.0058658348682790705,"request":0.001,"image":0.0,"image_output":0.0,"web_search":3.450491098987689,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":1809.0510773060576,"max_completion_cost":5535.693950222588,"max_cost":5716.599748051413},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.3-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":9.075000000000001e-7,"completion":4.537500000000001e-6,"request":0.0,"image":9.075000000000001e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":4.537500000000001e-6,"input_cache_read":9.075000000000002e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.9515827200000001,"max_completion_cost":0.29736960000000007,"max_cost":1.1894784000000003},"sats_pricing":{"prompt":0.0011386620626659375,"completion":0.005693310313329688,"request":0.001,"image":0.0011386620626659375,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.005693310313329688,"input_cache_read":0.00011386620626659374,"input_cache_write":0.00005750818498312819,"max_prompt_cost":1193.973711021998,"max_completion_cost":373.1167846943744,"max_cost":1492.4671387774977},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.8-flash-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.8-flash:batch","name":"Google: Gemini 3.8 Flash (batch)","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":2.0625e-6,"request":0.0,"image":4.125e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":2.0625e-6,"input_cache_read":4.125e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.4325376,"max_completion_cost":0.135168,"max_cost":0.540672},"sats_pricing":{"prompt":0.0005175736648481533,"completion":0.0025878683242407667,"request":0.001,"image":0.0005175736648481533,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0025878683242407667,"input_cache_read":0.000051757366484815334,"input_cache_write":0.00005750818498312819,"max_prompt_cost":542.7153231918172,"max_completion_cost":169.5985384974429,"max_cost":678.3941539897716},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.8-flash-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-fable-5.1:batch","name":"Anthropic: Claude Fable 5.1 (batch)","created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00017252455494938445,"input_cache_write":0.008626227747469224,"max_prompt_cost":6900.982197975379,"max_completion_cost":4416.628606704242,"max_cost":10434.285083338771},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-fable-5.1-20260831","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"granite-4.2-8b","name":"IBM: Granite 4.2 8B","created":1788206780,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":2.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.008650752,"max_completion_cost":0.0324401,"max_cost":0.033305228},"sats_pricing":{"prompt":0.00008281178637570452,"completion":0.0003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002070294659392613,"input_cache_write":0.0,"max_prompt_cost":10.854306463836343,"max_completion_cost":40.70337320009837,"max_cost":41.78887009591111},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"ibm-granite/granite-4.2-8b-20260831","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-flash-latest","name":"Z.ai: GLM Flash Latest","created":1787817633,"description":"This model always redirects to the latest model in the GLM Flash family.","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":3.1350000000000006e-8,"completion":1.0153000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.1350000000000006e-8,"input_cache_write":0.0,"max_prompt_cost":0.032872857600000006,"max_completion_cost":0.013307740160000001,"max_cost":0.04207149056000001},"sats_pricing":{"prompt":0.00003933559852845966,"completion":0.00012739213137462547,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003933559852845966,"input_cache_write":0.0,"max_prompt_cost":41.246364562578115,"max_completion_cost":16.69754144353491,"max_cost":52.78811043579076},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~z-ai/glm-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"glm-5.3-flash:batch","name":"Z.ai: GLM 5.3 Flash (batch)","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":1.9800000000000003e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.025952256000000003,"max_cost":0.07641497600000001},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.0002484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.0,"max_prompt_cost":72.3620430922423,"max_completion_cost":32.562919391509034,"max_cost":95.87970709722104},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","created":1787336476,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":2.2000000000000003e-9,"input_cache_write":0.0,"max_prompt_cost":0.11534336,"max_completion_cost":0.20761796000000002,"max_cost":0.21915234000000003},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":3.450491098987689,"internal_reasoning":0.0,"input_cache_read":2.7603928791901512e-6,"input_cache_write":0.0,"max_prompt_cost":144.7240861844846,"max_completion_cost":260.50324471635713,"max_cost":274.97570854266314},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.2-contributor-20260805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":2.3716000000000001e-7,"completion":7.114800000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.546e-9,"input_cache_write":0.0,"max_prompt_cost":0.24868028416000001,"max_completion_cost":0.18651021312000002,"max_cost":0.37302042624000004},"sats_pricing":{"prompt":0.0002975703523766983,"completion":0.000892711057130095,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.468147575622217e-6,"input_cache_write":0.0,"max_prompt_cost":312.0251298137488,"max_completion_cost":234.0188473603116,"max_cost":468.0376947206232},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp-20260821","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"hy-mt2-1.8b","name":"Tencent: Hy-MT2-1.8B","created":1787231581,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.84e-8,"completion":1.9470000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0003964928,"max_completion_cost":0.0007974912000000001,"max_cost":0.0009957376},"sats_pricing":{"prompt":0.000060728643342183324,"completion":0.0002442947698083284,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.4974890462591658,"max_completion_cost":1.0006313771349131,"max_cost":1.2493759002644957},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-1.8b-20260521","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"hy-mt2-30b-a3b","name":"Tencent: Hy-MT2-30B-A3B","created":1787231561,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.14e-8,"completion":3.2450000000000003e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0006668288,"max_completion_cost":0.0013291520000000001,"max_cost":0.0016625664},"sats_pricing":{"prompt":0.00010213453653003559,"completion":0.0004071579496805473,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.8366861232540516,"max_completion_cost":1.6677189618915218,"max_cost":2.086062023518547},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-30b-a3b-20260521","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-latest","name":"Z.ai: GLM Latest","created":1787151053,"description":"This model always redirects to the latest GLM model from Z.ai.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":7.689000000000001e-8,"completion":1.54e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.579e-8,"input_cache_write":0.0,"max_prompt_cost":0.08062500864000001,"max_completion_cost":1.45332572,"max_cost":1.46138825162},"sats_pricing":{"prompt":0.00009647573112769578,"completion":0.0019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000950955346881007,"input_cache_write":0.0,"max_prompt_cost":101.16213624295473,"max_completion_cost":1823.5227130144997,"max_cost":1833.6389652290877},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~z-ai/glm-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"hy-mt2-7b","name":"Tencent: Hy-MT2-7B","created":1787148797,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.14e-8,"completion":3.2450000000000003e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0006668288,"max_completion_cost":0.0013291520000000001,"max_cost":0.0016625664},"sats_pricing":{"prompt":0.00010213453653003559,"completion":0.0004071579496805473,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.8366861232540516,"max_completion_cost":1.6677189618915218,"max_cost":2.086062023518547},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-7b-20260521","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5.3:batch","name":"Z.ai: GLM 5.3 (batch)","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.95e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.51904512,"max_completion_cost":0.2883584,"max_cost":0.7425228800000001},"sats_pricing":{"prompt":0.000621088397817784,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":651.2583878301807,"max_completion_cost":361.8102154612115,"max_cost":931.6613048126196},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-20260816","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"qwen3.8-27b","name":"Qwen: Qwen3.8 27B","created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","context_length":1024000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":2.0625e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.48660356250000003,"max_cost":0.49092903750000005},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0025878683242407667,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000051757366484815334,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":610.5531858697998,"max_cost":615.9804633193976},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-27b-20260814","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","low","none"],"default_effort":"xhigh"},"image_pricing":null},{"id":"gemini-3.7-flash","name":"Google: Gemini 3.7 Flash","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.125e-6,"request":0.0,"image":8.25e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":4.125e-6,"input_cache_read":8.25e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.8650752,"max_completion_cost":0.270336,"max_cost":1.081344},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.0051757366484815335,"request":0.001,"image":0.0010351473296963066,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0051757366484815335,"input_cache_read":0.00010351473296963067,"input_cache_write":0.00005750818498312819,"max_prompt_cost":1085.4306463836344,"max_completion_cost":339.1970769948858,"max_cost":1356.788307979543},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.7-flash-20260813","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.7-flash:batch","name":"Google: Gemini 3.7 Flash (batch)","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":2.0625e-6,"request":0.0,"image":4.125e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":2.0625e-6,"input_cache_read":4.125e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.4325376,"max_completion_cost":0.135168,"max_cost":0.540672},"sats_pricing":{"prompt":0.0005175736648481533,"completion":0.0025878683242407667,"request":0.001,"image":0.0005175736648481533,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0025878683242407667,"input_cache_read":0.000051757366484815334,"input_cache_write":0.00005750818498312819,"max_prompt_cost":542.7153231918172,"max_completion_cost":169.5985384974429,"max_cost":678.3941539897716},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.7-flash-20260813","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.3068672,"max_completion_cost":0.8650752,"max_cost":2.8835840000000004},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":2894.481723689692,"max_completion_cost":1085.4306463836344,"max_cost":3618.102154612115},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-2.4t-a95b-20260812","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","medium","low"],"default_effort":"xhigh"},"image_pricing":null},{"id":"seed-2.0-code","name":"ByteDance Seed: Seed-2.0-Code","created":1786550701,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.4325376,"max_cost":0.5046272},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.004140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":542.7153231918172,"max_cost":633.1678770571201},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-code-20260730","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"grok-4.6:batch","name":"SpaceXAI: Grok 4.6 (batch)","created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.76e-6,"completion":5.28e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":0.0,"max_prompt_cost":0.88,"max_completion_cost":2.3760000000000003,"max_cost":2.4640000000000004},"sats_pricing":{"prompt":0.002208314303352121,"completion":0.006624942910056363,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.0005520785758380303,"input_cache_write":0.0,"max_prompt_cost":1104.1571516760605,"max_completion_cost":2981.2243095253634,"max_cost":3091.6400246929697},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.6-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"lfm-2.5-2.6b","name":"LiquidAI: LFM2.5-2.6B","created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.85e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.049280000000000004,"max_completion_cost":0.0045056,"max_cost":0.05063168},"sats_pricing":{"prompt":0.00048306875385827644,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":61.83280049385939,"max_completion_cost":5.65328461658143,"max_cost":63.52878587883381},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"liquid/lfm-2.5-2.6b-20260811","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.700000000000001e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.020185088000000004,"max_completion_cost":0.05190438,"max_cost":0.053922935},"sats_pricing":{"prompt":0.0000966137507716553,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":25.326715082284807,"max_completion_cost":65.12567315944531,"max_cost":67.65840263592425},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"sakana-namazu","name":"Sakana: Sakana Namazu","created":1786410129,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.0450000000000002e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.007700000000000001,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.27394048000000004,"max_completion_cost":0.2883584,"max_cost":0.49381376000000005},"sats_pricing":{"prompt":0.001311186617615322,"completion":0.005520785758380302,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.66137507716553,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":343.71970468815096,"max_completion_cost":361.8102154612115,"max_cost":619.5999939773247},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/namazu-20260811","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"solar-pro4","name":"Upstage: Solar Pro 4","created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.08650752,"max_completion_cost":0.08650752,"max_cost":0.15138816},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":108.54306463836345,"max_completion_cost":108.54306463836345,"max_cost":189.95036311713602},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"upstage/solar-pro4-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"ling-3.0-tiny","name":"inclusionAI: Ling 3.0 Tiny","created":1786034890,"description":"Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-8,"completion":4.9500000000000006e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-9,"input_cache_write":0.0,"max_prompt_cost":0.004325376,"max_completion_cost":0.012375000000000002,"max_cost":0.012575376000000003},"sats_pricing":{"prompt":0.00002070294659392613,"completion":0.0000621088397817784,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.140589318785227e-6,"input_cache_write":0.0,"max_prompt_cost":5.4271532319181714,"max_completion_cost":15.527209945444602,"max_cost":15.778626528881242},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":250000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-tiny-20260806","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"muse-spark-1.2","name":"Meta: Muse Spark 1.2","created":1785959287,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":4.675e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":1.4417920000000002,"max_completion_cost":4.41188165,"max_cost":4.5560614},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.0058658348682790705,"request":0.001,"image":0.0,"image_output":0.0,"web_search":3.450491098987689,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":1809.0510773060576,"max_completion_cost":5535.693950222588,"max_cost":5716.599748051413},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.2-20260805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"deepseek-v4-flash-latest","name":"DeepSeek: DeepSeek V4 Flash Latest","created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":6.49e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.850000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.0680525824,"max_completion_cost":0.31142694000000004,"max_cost":0.3182322242},"sats_pricing":{"prompt":0.00008143158993610946,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004830687538582765,"input_cache_write":0.0,"max_prompt_cost":85.38721084884591,"max_completion_cost":390.7548670745357,"max_cost":399.29362073205624},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-v4-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"inkling-small","name":"Thinking Machines: Inkling Small","created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","context_length":524288,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.95e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.25952256,"max_completion_cost":0.34603008,"max_cost":0.47579136},"sats_pricing":{"prompt":0.000621088397817784,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":325.62919391509035,"max_completion_cost":434.1722585534538,"max_cost":596.9868555109989},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thinkingmachines/inkling-small-20260730","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.7-flash","name":"Qwen: Qwen3.7 Flash","created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":3.3e-8,"completion":1.4300000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-9,"input_cache_write":4.1800000000000004e-8,"max_prompt_cost":0.032999999999999995,"max_completion_cost":0.009371648000000002,"max_cost":0.04020896},"sats_pricing":{"prompt":0.00004140589318785226,"completion":0.00017942553714735983,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.281178637570454e-6,"input_cache_write":0.00005244746470461287,"max_prompt_cost":41.40589318785226,"max_completion_cost":11.758832002489374,"max_cost":50.45114857438255},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-flash-20260727","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"image_pricing":null},{"id":"claude-opus-5:batch","name":"Anthropic: Claude Opus 5 (batch)","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.7600000000000002,"max_cost":4.158},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.017252455494938448,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.004313113873734612,"max_prompt_cost":3450.4910989876894,"max_completion_cost":2208.314303352121,"max_cost":5217.1425416693855},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5-20260723","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"ling-3.0-flash","name":"inclusionAI: Ling 3.0 Flash","created":1784818580,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.3100000000000002e-8,"completion":6.93e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.620000000000001e-9,"input_cache_write":0.0,"max_prompt_cost":0.0060555264000000004,"max_completion_cost":0.0022708224,"max_cost":0.007569408000000001},"sats_pricing":{"prompt":0.000028984125231496586,"completion":0.00008695237569448976,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.796825046299318e-6,"input_cache_write":0.0,"max_prompt_cost":7.598014524685441,"max_completion_cost":2.8492554467570406,"max_cost":9.497518155856802},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-flash-20260723","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.125e-6,"request":0.0,"image":8.25e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":4.125e-6,"input_cache_read":8.25e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.8650752,"max_completion_cost":0.270336,"max_cost":1.081344},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.0051757366484815335,"request":0.001,"image":0.0010351473296963066,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0051757366484815335,"input_cache_read":0.00010351473296963067,"input_cache_write":0.00005750818498312819,"max_prompt_cost":1085.4306463836344,"max_completion_cost":339.1970769948858,"max_cost":1356.788307979543},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.6-flash-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.6-flash:batch","name":"Google: Gemini 3.6 Flash (batch)","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":2.0625e-6,"request":0.0,"image":4.125e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":2.0625e-6,"input_cache_read":4.125e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.4325376,"max_completion_cost":0.135168,"max_cost":0.540672},"sats_pricing":{"prompt":0.0005175736648481533,"completion":0.0025878683242407667,"request":0.001,"image":0.0005175736648481533,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0025878683242407667,"input_cache_read":0.000051757366484815334,"input_cache_write":0.00005750818498312819,"max_prompt_cost":542.7153231918172,"max_completion_cost":169.5985384974429,"max_cost":678.3941539897716},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.6-flash-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":3.3e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":2.7500000000000004e-6,"input_cache_read":3.3e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.34603008,"max_completion_cost":0.18022400000000002,"max_cost":0.5046272},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.003450491098987689,"request":0.001,"image":0.00041405893187852267,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.003450491098987689,"input_cache_read":0.00004140589318785226,"input_cache_write":0.00011501636996625625,"max_prompt_cost":434.1722585534538,"max_completion_cost":226.1313846632572,"max_cost":633.1678770571201},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-lite-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"image_pricing":null},{"id":"gemini-3.5-flash-lite:batch","name":"Google: Gemini 3.5 Flash Lite (batch)","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":1.65e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":1.3750000000000002e-6,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.09011200000000001,"max_cost":0.2523136},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0017252455494938446,"request":0.001,"image":0.00020702946593926133,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0017252455494938446,"input_cache_read":0.00002070294659392613,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":113.0656923316286,"max_cost":316.58393852856005},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-lite-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"image_pricing":null},{"id":"longcat-2.0","name":"Meituan: LongCat 2.0","created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","context_length":1048756,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-9,"input_cache_write":0.0,"max_prompt_cost":0.34608948,"max_completion_cost":0.34603008,"max_cost":0.60561204},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.281178637570454e-6,"input_cache_write":0.0,"max_prompt_cost":434.2467891611919,"max_completion_cost":434.1722585534538,"max_cost":759.8759830762822},"per_request_limits":null,"top_provider":{"context_length":1048756,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meituan/longcat-2.0-20260720","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"image_pricing":null},{"id":"kimi-k3:batch","name":"MoonshotAI: Kimi K3 (batch)","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.5080000000000004e-6,"completion":0.00001254,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.5080000000000005e-7,"input_cache_write":0.0,"max_prompt_cost":2.6298286080000004,"max_completion_cost":0.20545536,"max_cost":2.7941928960000006},"sats_pricing":{"prompt":0.0031468478822767724,"completion":0.01573423941138386,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00031468478822767727,"input_cache_write":0.0,"max_prompt_cost":3299.709165006249,"max_completion_cost":257.7897785161132,"max_cost":3505.94098781914},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k3-20260715","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"muse-spark-1.1","name":"Meta: Muse Spark 1.1","created":1784215741,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":4.675e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0027500000000000003,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":1.4417920000000002,"max_completion_cost":4.41188165,"max_cost":4.5560614},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.0058658348682790705,"request":0.001,"image":0.0,"image_output":0.0,"web_search":3.450491098987689,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":1809.0510773060576,"max_completion_cost":5535.693950222588,"max_cost":5716.599748051413},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.1-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":2.75e-7,"max_prompt_cost":0.231,"max_completion_cost":0.16896,"max_cost":0.3718},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0003450491098987689,"max_prompt_cost":289.84125231496586,"max_completion_cost":211.9981731218036,"max_cost":466.50639658313554},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-luna-pro:batch","name":"OpenAI: GPT-5.6 Luna Pro (batch)","created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.1155,"max_completion_cost":0.08448,"max_cost":0.1859},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.0,"max_prompt_cost":144.92062615748293,"max_completion_cost":105.9990865609018,"max_cost":233.25319829156777},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":2.75e-7,"max_prompt_cost":0.231,"max_completion_cost":0.16896,"max_cost":0.3718},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0003450491098987689,"max_prompt_cost":289.84125231496586,"max_completion_cost":211.9981731218036,"max_cost":466.50639658313554},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-luna-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-luna:batch","name":"OpenAI: GPT-5.6 Luna (batch)","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.1155,"max_completion_cost":0.08448,"max_cost":0.1859},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.0,"max_prompt_cost":144.92062615748293,"max_completion_cost":105.9990865609018,"max_cost":233.25319829156777},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-luna-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.6896,"max_cost":3.718},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.016562357275140906,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":2119.9817312180357,"max_cost":4665.063965831355},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-terra-pro:batch","name":"OpenAI: GPT-5.6 Terra Pro (batch)","created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":1.155,"max_completion_cost":0.8448,"max_cost":1.859},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":1449.2062615748293,"max_completion_cost":1059.9908656090179,"max_cost":2332.5319829156774},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.6896,"max_cost":3.718},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.016562357275140906,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":2119.9817312180357,"max_cost":4665.063965831355},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-terra-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-terra:batch","name":"OpenAI: GPT-5.6 Terra (batch)","created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":1.155,"max_completion_cost":0.8448,"max_cost":1.859},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":1449.2062615748293,"max_completion_cost":1059.9908656090179,"max_cost":2332.5319829156774},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-terra-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":4.4e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.62,"max_completion_cost":2.8160000000000003,"max_cost":6.8728},"sats_pricing":{"prompt":0.005520785758380302,"completion":0.027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0005520785758380303,"input_cache_write":0.006900982197975378,"max_prompt_cost":5796.825046299317,"max_completion_cost":3533.3028853633937,"max_cost":8623.467354590031},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-sol-pro:batch","name":"OpenAI: GPT-5.6 Sol Pro (batch)","created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","created":1791409199,"description":"GPT-5.6 Sol via openai-codex","context_length":922000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":2.6e-6,"completion":0.000013000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.6000000000000005e-7,"input_cache_write":3.2500000000000002e-6,"max_prompt_cost":2.3972,"max_completion_cost":1.6640000000000001,"max_cost":3.7284},"sats_pricing":{"prompt":0.0032622824935883603,"completion":0.0163114124679418,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00032622824935883606,"input_cache_write":0.00407785311698545,"max_prompt_cost":3007.8244590884683,"max_completion_cost":2087.860795896551,"max_cost":4678.113095805708},"per_request_limits":null,"top_provider":{"context_length":922000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"generic","canonical_slug":null,"alias_ids":null,"forwarded_model_id":"openai/gpt-5.6-sol","image_pricing":null},{"id":"gpt-5.6-sol:batch","name":"OpenAI: GPT-5.6 Sol (batch)","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.31,"max_completion_cost":1.4080000000000001,"max_cost":3.4364},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.003450491098987689,"max_prompt_cost":2898.4125231496587,"max_completion_cost":1766.6514426816968,"max_cost":4311.733677295016},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.6-sol-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"grok-latest","name":"xAI: Grok Latest","created":1783519360,"description":"This model always redirects to the latest Grok model from xAI.","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":2.97,"max_cost":3.08},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":1380.1964395950756,"max_completion_cost":3726.530386906704,"max_cost":3864.5500308662113},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~x-ai/grok-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","created":1783443096,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.7e-7,"completion":1.54e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9800000000000003e-7,"input_cache_write":0.0,"max_prompt_cost":0.10092544,"max_completion_cost":0.05046272,"max_cost":0.1261568},"sats_pricing":{"prompt":0.0009661375077165529,"completion":0.0019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002484353591271136,"input_cache_write":0.0,"max_prompt_cost":126.63357541142402,"max_completion_cost":63.31678770571201,"max_cost":158.29196926428003},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.0-mini-20260707","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"aion-3.0","name":"AionLabs: Aion-3.0","created":1783443095,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.4325376,"max_completion_cost":0.2162688,"max_cost":0.540672},"sats_pricing":{"prompt":0.004140589318785227,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0010351473296963066,"input_cache_write":0.0,"max_prompt_cost":542.7153231918172,"max_completion_cost":271.3576615959086,"max_cost":678.3941539897716},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.0-20260707","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"hy3","name":"Tencent: Hy3","created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.452e-7,"completion":5.808e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.63e-8,"input_cache_write":0.0,"max_prompt_cost":0.0380633088,"max_completion_cost":0.0743424,"max_cost":0.0938201088},"sats_pricing":{"prompt":0.00018218593002654996,"completion":0.0007287437201061998,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004554648250663749,"input_cache_write":0.0,"max_prompt_cost":47.75894844087991,"max_completion_cost":93.27919617359359,"max_cost":117.71834557107509},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy3-20260706","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":1.3750000000000002e-6,"max_prompt_cost":1.1,"max_completion_cost":0.7040000000000001,"max_cost":1.6632000000000002},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0017252455494938446,"max_prompt_cost":1380.1964395950756,"max_completion_cost":883.3257213408484,"max_cost":2086.8570166677546},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5-20260630","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"gemini-3.1-flash-lite-image","name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","created":1782837225,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.000033,"web_search":0.015400000000000002,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.0180224,"max_completion_cost":0.0973203,"max_cost":0.09912264999999999},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.04140589318785227,"web_search":19.32275015433106,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0,"max_prompt_cost":22.61313846632572,"max_completion_cost":122.1101196002951,"max_cost":124.37157146657164},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-image-20260630","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"fugu-ultra","name":"Sakana: Fugu Ultra","created":1782276303,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":5.500000000000001,"max_completion_cost":4.224,"max_cost":9.02},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.04140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":6900.982197975379,"max_completion_cost":5299.95432804509,"max_cost":11317.610804679618},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-ultra-20260615","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"xhigh"},"image_pricing":null},{"id":"gemini-3.1-flash-image","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","created":1781754065,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","context_length":131072,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.000066,"web_search":0.015400000000000002,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.0720896,"max_completion_cost":0.1081344,"max_cost":0.1622016},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.004140589318785227,"request":0.001,"image":0.0,"image_output":0.08281178637570454,"web_search":19.32275015433106,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":90.45255386530287,"max_completion_cost":135.6788307979543,"max_cost":203.51824619693144},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-image-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"gemini-3-pro-image","name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","created":1781754054,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","context_length":131072,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":2.2e-6,"image_output":0.000132,"web_search":0.015400000000000002,"internal_reasoning":0.0000132,"input_cache_read":2.2e-7,"input_cache_write":4.125e-7,"max_prompt_cost":0.1441792,"max_completion_cost":0.4325376,"max_cost":0.5046272},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.016562357275140906,"request":0.001,"image":0.002760392879190151,"image_output":0.16562357275140907,"web_search":19.32275015433106,"internal_reasoning":0.016562357275140906,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0005175736648481533,"max_prompt_cost":180.90510773060575,"max_completion_cost":542.7153231918172,"max_cost":633.1678770571201},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-pro-image-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"claude-fable-latest","name":"Anthropic: Claude Fable Latest","created":1781029944,"description":"This model always redirects to the latest model in the Claude Fable family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.00005500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.000013750000000000002,"max_prompt_cost":11.000000000000002,"max_completion_cost":7.040000000000001,"max_cost":16.632},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.06900982197975379,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.017252455494938448,"max_prompt_cost":13801.964395950758,"max_completion_cost":8833.257213408484,"max_cost":20868.570166677542},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-fable-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":5.500000000000001,"max_completion_cost":3.5200000000000005,"max_cost":8.316},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.008626227747469224,"max_prompt_cost":6900.982197975379,"max_completion_cost":4416.628606704242,"max_cost":10434.285083338771},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-5-fable-20260609","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"nemotron-3.5-content-safety","name":"NVIDIA: Nemotron 3.5 Content Safety","created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.025952080000000002,"max_cost":0.02883584},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":32.5626985600787,"max_cost":36.18102154612115},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-content-safety-20260604","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"qwen3.7-plus:batch","name":"Qwen: Qwen3.7 Plus (batch)","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.53e-7,"completion":1.012e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.066322432,"max_completion_cost":0.132644864,"max_cost":0.16580608},"sats_pricing":{"prompt":0.00031744518110686737,"completion":0.0012697807244274695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":83.21634955607864,"max_completion_cost":166.43269911215728,"max_cost":208.0408738901966},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-plus-20260602","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"step-3.7-flash","name":"StepFun: Step 3.7 Flash","created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.2650000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.05632,"max_completion_cost":0.29145600000000005,"max_cost":0.2970880000000001},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.001587225905534337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":70.66605770726787,"max_completion_cost":365.6968486351113,"max_cost":372.7634544058381},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-3.7-flash-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.7600000000000002,"max_cost":4.158},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.017252455494938448,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.004313113873734612,"max_prompt_cost":3450.4910989876894,"max_completion_cost":2208.314303352121,"max_cost":5217.1425416693855},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.8-opus-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"grok-build-0.1","name":"SpaceXAI: Grok Build 0.1","created":1779298123,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","context_length":256000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":0.50688,"max_cost":0.53504},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":353.33028853633937,"max_completion_cost":635.9945193654107,"max_cost":671.3275482190446},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-build-0.1-20260520","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":9.900000000000002e-6,"request":0.0,"image":1.65e-6,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":9.900000000000002e-6,"input_cache_read":1.65e-7,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":1.7301504,"max_completion_cost":0.6488064000000001,"max_cost":2.2708224},"sats_pricing":{"prompt":0.0020702946593926133,"completion":0.01242176795635568,"request":0.001,"image":0.0020702946593926133,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.01242176795635568,"input_cache_read":0.00020702946593926133,"input_cache_write":0.00011501636996625625,"max_prompt_cost":2170.861292767269,"max_completion_cost":814.0729847877259,"max_cost":2849.2554467570403},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-20260519","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.5-flash:batch","name":"Google: Gemini 3.5 Flash (batch)","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.950000000000001e-6,"request":0.0,"image":8.25e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":4.950000000000001e-6,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.8650752,"max_completion_cost":0.32440320000000006,"max_cost":1.1354112},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.00621088397817784,"request":0.001,"image":0.0010351473296963066,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.00621088397817784,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":1085.4306463836344,"max_completion_cost":407.03649239386294,"max_cost":1424.6277233785202},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-20260519","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"perceptron-mk1","name":"Perceptron: Perceptron Mk1","created":1778597029,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","context_length":32768,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00540672,"max_completion_cost":0.0135168,"max_cost":0.017571840000000002},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.783941539897715,"max_completion_cost":16.959853849744288,"max_cost":22.047810004667575},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perceptron/perceptron-mk1-20260512","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.65e-6,"request":0.0,"image":2.75e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":1.65e-6,"input_cache_read":2.75e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.2883584,"max_completion_cost":0.1081344,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.0020702946593926133,"request":0.001,"image":0.0003450491098987689,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0020702946593926133,"input_cache_read":0.00003450491098987689,"input_cache_write":0.00011501636996625625,"max_prompt_cost":361.8102154612115,"max_completion_cost":135.6788307979543,"max_cost":474.8759077928401},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-20260507","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"gemini-3.1-flash-lite:batch","name":"Google: Gemini 3.1 Flash Lite (batch)","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.375e-7,"completion":8.25e-7,"request":0.0,"image":1.375e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":8.25e-7,"input_cache_read":1.375e-8,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.0540672,"max_cost":0.18923520000000002},"sats_pricing":{"prompt":0.00017252455494938445,"completion":0.0010351473296963066,"request":0.001,"image":0.00017252455494938445,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0010351473296963066,"input_cache_read":0.000017252455494938446,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":67.83941539897715,"max_cost":237.43795389642005},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-20260507","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"gpt-chat-latest","name":"OpenAI: GPT Chat Latest","created":1778000212,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":2.2,"max_completion_cost":4.224,"max_cost":5.720000000000001},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.04140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":2760.3928791901512,"max_completion_cost":5299.95432804509,"max_cost":7177.021485894394},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-chat-latest-20260505","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"grok-4.3:batch","name":"SpaceXAI: Grok 4.3 (batch)","created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":1.7600000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":1.9800000000000002,"max_cost":2.0900000000000003},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.0002208314303352121,"input_cache_write":0.0,"max_prompt_cost":1380.1964395950756,"max_completion_cost":2484.353591271136,"max_cost":2622.373235230644},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.3-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"low"},"image_pricing":null},{"id":"mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.4325376,"max_completion_cost":1.7301487500000001,"max_cost":1.8166566000000002},"sats_pricing":{"prompt":0.0020702946593926133,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":542.7153231918172,"max_completion_cost":2170.8592224726094,"max_cost":2279.402701169905},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.5-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"mistral-medium-3-5:batch","name":"Mistral: Mistral Medium 3.5 (batch)","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.125e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2162688,"max_completion_cost":0.8650743750000001,"max_cost":0.9083283000000001},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.0051757366484815335,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":271.3576615959086,"max_completion_cost":1085.4296112363047,"max_cost":1139.7013505849525},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.5-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-haiku-latest","name":"Anthropic: Claude Haiku Latest","created":1777318492,"description":"This model always redirects to the latest model in the Claude Haiku family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":1.375e-7,"max_prompt_cost":0.11,"max_completion_cost":0.0704,"max_cost":0.16632000000000002},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.00017252455494938445,"max_prompt_cost":138.01964395950756,"max_completion_cost":88.33257213408484,"max_cost":208.68570166677543},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-haiku-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-mini-latest","name":"OpenAI: GPT Mini Latest","created":1777318471,"description":"This model always redirects to the latest model in the GPT Mini family.","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.950000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.6336000000000002,"max_cost":0.8580000000000002},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.00621088397817784,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":414.0589318785227,"max_completion_cost":794.9931492067636,"max_cost":1076.5532228841591},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-mini-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-pro-latest","name":"Google: Gemini Pro Latest","created":1777318451,"description":"This model always redirects to the latest model in the Gemini Pro family.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":2.2e-6,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.000011000000000000001,"input_cache_read":1.1e-7,"input_cache_write":2.0625e-7,"max_prompt_cost":2.3068672,"max_completion_cost":10.380898000000002,"max_cost":10.611585600000002},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.002760392879190151,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.013801964395950756,"input_cache_read":0.00013801964395950757,"input_cache_write":0.00025878683242407666,"max_prompt_cost":2894.481723689692,"max_completion_cost":13025.162235817857,"max_cost":13314.611512343978},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~google/gemini-pro-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"kimi-latest","name":"MoonshotAI: Kimi Latest","created":1777318428,"description":"This model always redirects to the latest model in the Kimi family.","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.8909e-7,"completion":0.00001027268,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.87e-7,"input_cache_write":0.0,"max_prompt_cost":0.19827523584,"max_completion_cost":9.694513024239999,"max_cost":9.714340623459998},"sats_pricing":{"prompt":0.00023725576796639349,"completion":0.01288937851009049,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002346333947311628,"input_cache_write":0.0,"max_prompt_cost":248.78070415112902,"max_completion_cost":12163.938508785577,"max_cost":12188.816674102996},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~moonshotai/kimi-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"gemini-flash-latest","name":"Google: Gemini Flash Latest","created":1777318398,"description":"This model always redirects to the latest model in the Gemini Flash family.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.125e-6,"request":0.0,"image":8.25e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":4.125e-6,"input_cache_read":8.25e-8,"input_cache_write":4.583333333333337e-8,"max_prompt_cost":0.8650752,"max_completion_cost":0.270336,"max_cost":1.081344},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.0051757366484815335,"request":0.001,"image":0.0010351473296963066,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0051757366484815335,"input_cache_read":0.00010351473296963067,"input_cache_write":0.00005750818498312819,"max_prompt_cost":1085.4306463836344,"max_completion_cost":339.1970769948858,"max_cost":1356.788307979543},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~google/gemini-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-sonnet-latest","name":"Anthropic: Claude Sonnet Latest","created":1777318368,"description":"This model always redirects to the latest model in the Claude Sonnet family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":2.7500000000000004e-6,"max_prompt_cost":2.2,"max_completion_cost":1.4080000000000001,"max_cost":3.3264000000000005},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.003450491098987689,"max_prompt_cost":2760.3928791901512,"max_completion_cost":1766.6514426816968,"max_cost":4173.714033335509},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-sonnet-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.98e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":4.125e-7,"max_prompt_cost":0.33,"max_completion_cost":0.12976128,"max_cost":0.43813440000000003},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.002484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0005175736648481533,"max_prompt_cost":414.0589318785227,"max_completion_cost":162.81459695754518,"max_cost":549.737762676477},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-plus-20260420","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.0625e-7,"completion":1.2375000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":2.578125e-7,"max_prompt_cost":0.20625000000000002,"max_completion_cost":0.08110080000000001,"max_cost":0.273834},"sats_pricing":{"prompt":0.00025878683242407666,"completion":0.00155272099454446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.00032348354053009584,"max_prompt_cost":258.7868324240767,"max_completion_cost":101.75912309846574,"max_cost":343.5861016727981},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.23356971,"max_cost":0.23645336},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.001242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":293.0655292175039,"max_cost":296.6837141839024},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-35b-a3b-20260415","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"qwen3.6-27b","name":"Qwen: Qwen3.6 27B","created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":4.95e-7,"completion":2.9700000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.12976128,"max_completion_cost":0.19464192000000002,"max_cost":0.29196288000000004},"sats_pricing":{"prompt":0.000621088397817784,"completion":0.003726530386906704,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":162.81459695754518,"max_completion_cost":244.22189543631777,"max_cost":366.3328431544767},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-27b-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000033,"completion":0.00019800000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":34.650000000000006,"max_completion_cost":25.344,"max_cost":55.77},"sats_pricing":{"prompt":0.04140589318785227,"completion":0.2484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":43476.18784724489,"max_completion_cost":31799.72596827054,"max_cost":69975.95948747033},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.5-pro-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.5-pro:batch","name":"OpenAI: GPT-5.5 Pro (batch)","created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000165,"completion":0.00009900000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.325000000000003,"max_completion_cost":12.672,"max_cost":27.885},"sats_pricing":{"prompt":0.020702946593926134,"completion":0.1242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":21738.093923622444,"max_completion_cost":15899.86298413527,"max_cost":34987.979743735166},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.5-pro-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.5","name":"OpenAI: GPT-5.5","created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000033,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":5.775,"max_completion_cost":4.224,"max_cost":9.295000000000002},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.04140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":7246.0313078741465,"max_completion_cost":5299.95432804509,"max_cost":11662.65991457839},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.5-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.5:batch","name":"OpenAI: GPT-5.5 (batch)","created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.8875,"max_completion_cost":2.112,"max_cost":4.647500000000001},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":3623.0156539370732,"max_completion_cost":2649.977164022545,"max_cost":5831.329957289195},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.5-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"hy3-preview","name":"Tencent: Hy3 preview","created":1776878150,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.9800000000000003e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.6e-8,"input_cache_write":0.0,"max_prompt_cost":0.05190451200000001,"max_completion_cost":0.15571314,"max_cost":0.16090371},"sats_pricing":{"prompt":0.0002484353591271136,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00008281178637570452,"input_cache_write":0.0,"max_prompt_cost":65.12583878301807,"max_completion_cost":195.37701947833594,"max_cost":201.88975241785323},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy3-preview-20260421","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","context_length":1050000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.28e-7,"completion":1.98e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.056e-7,"input_cache_write":0.0,"max_prompt_cost":0.138412032,"max_completion_cost":0.46713942,"max_cost":0.48098094},"sats_pricing":{"prompt":0.0006624942910056362,"completion":0.002484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013249885820112726,"input_cache_write":0.0,"max_prompt_cost":173.6689034213815,"max_completion_cost":586.1310584350078,"max_cost":603.4983462737206},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.5-pro-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mimo-v2.5","name":"Xiaomi: MiMo-V2.5","created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","context_length":1000000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.800000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.44,"max_completion_cost":0.1441792,"max_cost":0.55534336},"sats_pricing":{"prompt":0.0005520785758380303,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00011041571516760605,"input_cache_write":0.0,"max_prompt_cost":552.0785758380302,"max_completion_cost":180.90510773060575,"max_cost":696.8026620225147},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.5-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gpt-5.4-image-2","name":"OpenAI: GPT-5.4 Image 2","created":1776797528,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","context_length":272000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.8e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.000033,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-6,"input_cache_write":0.0,"max_prompt_cost":2.3936,"max_completion_cost":2.112,"max_cost":3.3792},"sats_pricing":{"prompt":0.011041571516760605,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.04140589318785227,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.002760392879190151,"input_cache_write":0.0,"max_prompt_cost":3003.3074525588845,"max_completion_cost":2649.977164022545,"max_cost":4239.9634624360715},"per_request_limits":null,"top_provider":{"context_length":272000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-image-2-20260421","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-opus-latest","name":"Anthropic: Claude Opus Latest","created":1776795361,"description":"This model always redirects to the latest model in the Claude Opus family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":4.4e-6,"completion":0.000022000000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":5.500000000000001e-6,"max_prompt_cost":4.4,"max_completion_cost":2.8160000000000003,"max_cost":6.652800000000001},"sats_pricing":{"prompt":0.005520785758380302,"completion":0.027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.006900982197975378,"max_prompt_cost":5520.7857583803025,"max_completion_cost":3533.3028853633937,"max_cost":8347.428066671018},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-opus-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.7600000000000002,"max_cost":4.158},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.017252455494938448,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.004313113873734612,"max_prompt_cost":3450.4910989876894,"max_completion_cost":2208.314303352121,"max_cost":5217.1425416693855},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.7-opus-20260416","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","created":1775061458,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","context_length":202752,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.64e-7,"input_cache_write":0.0,"max_prompt_cost":0.26763264000000003,"max_completion_cost":0.5767168,"max_cost":0.6713344},"sats_pricing":{"prompt":0.0016562357275140907,"completion":0.005520785758380302,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003312471455028181,"input_cache_write":0.0,"max_prompt_cost":335.80510622493694,"max_completion_cost":723.620430922423,"max_cost":842.339407870633},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5v-turbo-20260401","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"grok-4.20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","created":1774979158,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","context_length":2000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":2.7500000000000004,"max_completion_cost":4.950000000000001,"max_cost":5.225000000000001},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":3450.4910989876894,"max_completion_cost":6210.883978177841,"max_cost":6555.93308807661},"per_request_limits":null,"top_provider":{"context_length":2000000,"max_completion_tokens":1800000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.20-multi-agent-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"grok-4.20","name":"SpaceXAI: Grok 4.20","created":1774979019,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","context_length":2000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":2.7500000000000004,"max_completion_cost":4.950000000000001,"max_cost":5.225000000000001},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":3450.4910989876894,"max_completion_cost":6210.883978177841,"max_cost":6555.93308807661},"per_request_limits":null,"top_provider":{"context_length":2000000,"max_completion_tokens":1800000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.20-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"reka-edge","name":"Reka Edge","created":1774026965,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","context_length":16384,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":1.1e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00180224,"max_completion_cost":0.00162195,"max_cost":0.00180224},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00013801964395950757,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.261313846632572,"max_completion_cost":2.035099650182939,"max_cost":2.261313846632572},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"rekaai/reka-edge-2603","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.08800000000000001,"max_completion_cost":0.17600000000000002,"max_cost":0.23584000000000002},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0,"max_prompt_cost":110.41571516760605,"max_completion_cost":220.8314303352121,"max_cost":295.9141166491842},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-nano-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-nano:batch","name":"OpenAI: GPT-5.4 Nano (batch)","created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":6.875000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.044000000000000004,"max_completion_cost":0.08800000000000001,"max_cost":0.11792000000000001},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0008626227747469223,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.0,"max_prompt_cost":55.207857583803026,"max_completion_cost":110.41571516760605,"max_cost":147.9570583245921},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-nano-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":4.950000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.6336000000000002,"max_cost":0.8580000000000002},"sats_pricing":{"prompt":0.0010351473296963066,"completion":0.00621088397817784,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":414.0589318785227,"max_completion_cost":794.9931492067636,"max_cost":1076.5532228841591},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-mini-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-mini:batch","name":"OpenAI: GPT-5.4 Mini (batch)","created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.125e-7,"completion":2.4750000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.3168000000000001,"max_cost":0.4290000000000001},"sats_pricing":{"prompt":0.0005175736648481533,"completion":0.00310544198908892,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000051757366484815334,"input_cache_write":0.0,"max_prompt_cost":207.02946593926134,"max_completion_cost":397.4965746033818,"max_cost":538.2766114420796},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-mini-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"mistral-small-2603","name":"Mistral: Mistral Small 4","created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.1384119,"max_cost":0.147062685},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002070294659392613,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":173.66873779780875,"max_cost":184.52308566753828},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-2603","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-5-turbo","name":"Z.ai: GLM 5 Turbo","created":1773583573,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.64e-7,"input_cache_write":0.0,"max_prompt_cost":0.26763264000000003,"max_completion_cost":0.5767168,"max_cost":0.6713344},"sats_pricing":{"prompt":0.0016562357275140907,"completion":0.005520785758380302,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003312471455028181,"input_cache_write":0.0,"max_prompt_cost":335.80510622493694,"max_completion_cost":723.620430922423,"max_cost":842.339407870633},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5-turbo-20260315","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.64e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.34603008,"max_completion_cost":0.69206016,"max_cost":0.95158272},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0033124714550281814,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":434.1722585534538,"max_completion_cost":868.3445171069076,"max_cost":1193.9737110219978},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["medium","low","none"],"default_effort":"medium","supports_max_tokens":true},"image_pricing":null},{"id":"seed-2.0-lite","name":"ByteDance Seed: Seed-2.0-Lite","created":1773157231,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0720896,"max_completion_cost":0.2883584,"max_cost":0.3244032},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":90.45255386530287,"max_completion_cost":361.8102154612115,"max_cost":407.0364923938629},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-lite-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000033,"completion":0.00019800000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":34.650000000000006,"max_completion_cost":25.344,"max_cost":55.77},"sats_pricing":{"prompt":0.04140589318785227,"completion":0.2484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":43476.18784724489,"max_completion_cost":31799.72596827054,"max_cost":69975.95948747033},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-pro-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-pro:batch","name":"OpenAI: GPT-5.4 Pro (batch)","created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000165,"completion":0.00009900000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":17.325000000000003,"max_completion_cost":12.672,"max_cost":27.885},"sats_pricing":{"prompt":0.020702946593926134,"completion":0.1242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":21738.093923622444,"max_completion_cost":15899.86298413527,"max_cost":34987.979743735166},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-pro-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4","name":"OpenAI: GPT-5.4","created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":2.8875,"max_completion_cost":2.112,"max_cost":4.647500000000001},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":3623.0156539370732,"max_completion_cost":2649.977164022545,"max_cost":5831.329957289195},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4:batch","name":"OpenAI: GPT-5.4 (batch)","created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":1.44375,"max_completion_cost":1.056,"max_cost":2.3237500000000004},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0,"max_prompt_cost":1811.5078269685366,"max_completion_cost":1324.9885820112725,"max_cost":2915.6649786445973},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.4-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","created":1772512673,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.65e-6,"request":0.0,"image":2.75e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":1.65e-6,"input_cache_read":2.75e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.2883584,"max_completion_cost":0.1081344,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.0020702946593926133,"request":0.001,"image":0.0003450491098987689,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0020702946593926133,"input_cache_read":0.00003450491098987689,"input_cache_write":0.00011501636996625625,"max_prompt_cost":361.8102154612115,"max_completion_cost":135.6788307979543,"max_cost":474.8759077928401},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-preview-20260303","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"seed-2.0-mini","name":"ByteDance Seed: Seed-2.0-Mini","created":1772131107,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.05767168,"max_cost":0.0720896},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":72.3620430922423,"max_cost":90.45255386530287},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-mini-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.1-flash-image-preview","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","created":1772119558,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.000066,"web_search":0.015400000000000002,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.0360448,"max_completion_cost":0.1946406,"max_cost":0.19824529999999999},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.004140589318785227,"request":0.001,"image":0.0,"image_output":0.08281178637570454,"web_search":19.32275015433106,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":45.22627693265144,"max_completion_cost":244.2202392005902,"max_cost":248.74314293314328},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-image-preview-20260226","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"qwen3.5-27b","name":"Qwen: Qwen3.5-27B","created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":2.86e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.07497318400000001,"max_completion_cost":0.2342912,"max_cost":0.28583526400000003},"sats_pricing":{"prompt":0.00035885107429471967,"completion":0.0035885107429471964,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":94.07065601991499,"max_completion_cost":293.97080006223433,"max_cost":358.6443760759259},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-27b-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":2.2880000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.07497318400000001,"max_completion_cost":0.14994636800000002,"max_cost":0.20617625600000003},"sats_pricing":{"prompt":0.00035885107429471967,"completion":0.0028708085943577573,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":94.07065601991499,"max_completion_cost":188.14131203982998,"max_cost":258.69430405476623},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-122b-a10b-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":7.150000000000001e-8,"completion":2.8600000000000005e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.07150000000000001,"max_completion_cost":0.018743296000000003,"max_cost":0.08555747200000002},"sats_pricing":{"prompt":0.00008971276857367992,"completion":0.00035885107429471967,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":89.71276857367991,"max_completion_cost":23.517664004978748,"max_cost":107.351016577414},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-flash-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","created":1772045923,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":2.2e-6,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.0000132,"input_cache_read":2.2e-7,"input_cache_write":4.125e-7,"max_prompt_cost":2.3068672,"max_completion_cost":0.8650752,"max_cost":3.0277632000000003},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.016562357275140906,"request":0.001,"image":0.002760392879190151,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.016562357275140906,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0005175736648481533,"max_prompt_cost":2894.481723689692,"max_completion_cost":1085.4306463836344,"max_cost":3799.007262342721},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-customtools-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","created":1771959164,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.7700000000000001,"max_completion_cost":1.9712000000000003,"max_cost":2.4948000000000006},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00024153437692913822,"input_cache_write":0.0,"max_prompt_cost":966.137507716553,"max_completion_cost":2473.312019754376,"max_cost":3130.285525001632},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.3-codex-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"aion-2.0","name":"AionLabs: Aion-2.0","created":1771881306,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":1.76e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.11534336,"max_completion_cost":0.05767168,"max_cost":0.1441792},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.002208314303352121,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":144.7240861844846,"max_completion_cost":72.3620430922423,"max_cost":180.90510773060575},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-2.0-20260223","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":2.2e-6,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.0000132,"input_cache_read":2.2e-7,"input_cache_write":4.125e-7,"max_prompt_cost":2.3068672,"max_completion_cost":0.8650752,"max_cost":3.0277632000000003},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.016562357275140906,"request":0.001,"image":0.002760392879190151,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.016562357275140906,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0005175736648481533,"max_prompt_cost":2894.481723689692,"max_completion_cost":1085.4306463836344,"max_cost":3799.007262342721},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.1-pro-preview:batch","name":"Google: Gemini 3.1 Pro Preview (batch)","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":6.6e-6,"request":0.0,"image":1.1e-6,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":6.6e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.1534336,"max_completion_cost":0.4325376,"max_cost":1.5138816000000002},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.008281178637570453,"request":0.001,"image":0.0013801964395950756,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.008281178637570453,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1447.240861844846,"max_completion_cost":542.7153231918172,"max_cost":1899.5036311713604},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-sonnet-4.6:batch","name":"Anthropic: Claude Sonnet 4.6 (batch)","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":2.0625e-6,"max_prompt_cost":1.6500000000000001,"max_completion_cost":1.056,"max_cost":2.4948},"sats_pricing":{"prompt":0.0020702946593926133,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0025878683242407667,"max_prompt_cost":2070.2946593926135,"max_completion_cost":1324.9885820112725,"max_cost":3130.2855250016314},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":1.7160000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.28600000000000003,"max_completion_cost":0.11245977600000001,"max_cost":0.3797164800000001},"sats_pricing":{"prompt":0.00035885107429471967,"completion":0.0021531064457683178,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":358.85107429471964,"max_completion_cost":141.10598402987247,"max_cost":476.4393943196134},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-plus-20260216","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"minimax-m2.5","name":"MiniMax: MiniMax M2.5","created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.97e-7,"completion":1.0450000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":4.125e-7,"max_prompt_cost":0.058806000000000004,"max_completion_cost":0.034242560000000005,"max_cost":0.083316464},"sats_pricing":{"prompt":0.00037265303869067043,"completion":0.001311186617615322,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0005175736648481533,"max_prompt_cost":73.78530166075274,"max_completion_cost":42.96496308601887,"max_cost":104.53916997495571},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.5-20260211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":2.7500000000000004,"max_completion_cost":1.7600000000000002,"max_cost":4.158},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.017252455494938448,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.004313113873734612,"max_prompt_cost":3450.4910989876894,"max_completion_cost":2208.314303352121,"max_cost":5217.1425416693855},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-opus-20260205","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"high","supports_max_tokens":true},"image_pricing":null},{"id":"qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":8.8e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.700000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.034603008,"max_completion_cost":0.20761752,"max_cost":0.2110779},"sats_pricing":{"prompt":0.00016562357275140904,"completion":0.0011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000966137507716553,"input_cache_write":0.0,"max_prompt_cost":43.41722585534537,"max_completion_cost":260.50269263778125,"max_cost":264.84451459745947},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-next-2025-02-03","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"step-3.5-flash","name":"StepFun: Step 3.5 Flash","created":1769728337,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.02162688,"max_cost":0.04325376},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":27.13576615959086,"max_cost":54.27153231918172},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-3.5-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"kimi-k2.5","name":"MoonshotAI: Kimi K2.5","created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.64880475,"max_cost":0.663223},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":814.0709144930664,"max_cost":832.1618393250588},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.5-0127","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"minimax-m2-her","name":"MiniMax: MiniMax M2-her","created":1769177239,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.00270336,"max_cost":0.0236544},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":27.13576615959086,"max_completion_cost":3.3919707699488577,"max_cost":29.679744237052503},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2-her-20260123","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"palmyra-x5","name":"Writer: Palmyra X5","created":1769003823,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","context_length":1040000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.6864,"max_completion_cost":0.0540672,"max_cost":0.73506048},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":861.2425783073271,"max_completion_cost":67.83941539897715,"max_cost":922.2980521664066},"per_request_limits":null,"top_provider":{"context_length":1040000,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"writer/palmyra-x5-20250428","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-audio","name":"OpenAI: GPT Audio","created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":441.6628606704242,"max_completion_cost":226.1313846632572,"max_cost":611.2613991678671},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-audio","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-audio-mini","name":"OpenAI: GPT Audio Mini","created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.64e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.08448,"max_completion_cost":0.04325376,"max_cost":0.11692032000000001},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.0033124714550281814,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":105.9990865609018,"max_completion_cost":54.27153231918172,"max_cost":146.7027358002881},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-audio-mini","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.655000000000001e-8,"completion":4.4e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.008722841600000001,"max_completion_cost":0.051904160000000005,"max_cost":0.052776497400000004},"sats_pricing":{"prompt":0.00008350188459550207,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":10.944759017701648,"max_completion_cost":65.1253971201574,"max_cost":66.21993982343524},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.7-flash-20260119","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","created":1768409315,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.7700000000000001,"max_completion_cost":1.9712000000000003,"max_cost":2.4948000000000006},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00024153437692913822,"input_cache_write":0.0,"max_prompt_cost":966.137507716553,"max_completion_cost":2473.312019754376,"max_cost":3130.285525001632},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-codex-20260114","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","created":1766505011,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02162688,"max_completion_cost":0.01081344,"max_cost":0.02973696},"sats_pricing":{"prompt":0.00010351473296963067,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":27.13576615959086,"max_completion_cost":13.56788307979543,"max_cost":37.31167846943743},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-1.6-flash-20250625","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"seed-1.6","name":"ByteDance Seed: Seed 1.6","created":1766504997,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0720896,"max_completion_cost":0.0720896,"max_cost":0.135168},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":90.45255386530287,"max_completion_cost":90.45255386530287,"max_cost":169.5985384974429},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-1.6-20250625","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"minimax-m2.1","name":"MiniMax: MiniMax M2.1","created":1766454997,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":4.125e-7,"max_prompt_cost":0.067584,"max_completion_cost":0.17301504,"max_cost":0.19734528},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0005175736648481533,"max_prompt_cost":84.79926924872144,"max_completion_cost":217.0861292767269,"max_cost":247.6138662062666},"per_request_limits":null,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-3-flash-preview:batch","name":"Google: Gemini 3 Flash Preview (batch)","created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":1.65e-6,"request":0.0,"image":2.75e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":1.65e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2883584,"max_completion_cost":0.1081344,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.0020702946593926133,"request":0.001,"image":0.0003450491098987689,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0020702946593926133,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":361.8102154612115,"max_completion_cost":135.6788307979543,"max_cost":474.8759077928401},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-flash-preview-20251217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":2.64e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.32e-8,"input_cache_write":0.0,"max_prompt_cost":0.017301504,"max_completion_cost":0.062285256,"max_cost":0.064015446},"sats_pricing":{"prompt":0.00008281178637570452,"completion":0.0003312471455028181,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000016562357275140907,"input_cache_write":0.0,"max_prompt_cost":21.708612927672686,"max_completion_cost":78.15080779133437,"max_cost":80.32171877117348},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","created":1765389783,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.24640000000000004,"max_completion_cost":0.49280000000000007,"max_cost":0.6776000000000001},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00024153437692913822,"input_cache_write":0.0,"max_prompt_cost":309.164002469297,"max_completion_cost":618.328004938594,"max_cost":850.2010067905666},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":32000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-chat-20251211","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000231,"completion":0.0001848,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.24,"max_completion_cost":23.6544,"max_cost":29.9376},"sats_pricing":{"prompt":0.028984125231496585,"completion":0.23187300185197268,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":11593.650092598635,"max_completion_cost":29679.744237052502,"max_cost":37563.42630001957},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-pro-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.2-pro:batch","name":"OpenAI: GPT-5.2 Pro (batch)","created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.00001155,"completion":0.0000924,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.62,"max_completion_cost":11.8272,"max_cost":14.9688},"sats_pricing":{"prompt":0.014492062615748293,"completion":0.11593650092598634,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5796.825046299317,"max_completion_cost":14839.872118526251,"max_cost":18781.713150009786},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-pro-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.2","name":"OpenAI: GPT-5.2","created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.925e-6,"completion":0.0000154,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.925e-7,"input_cache_write":0.0,"max_prompt_cost":0.7700000000000001,"max_completion_cost":1.9712000000000003,"max_cost":2.4948000000000006},"sats_pricing":{"prompt":0.0024153437692913822,"completion":0.019322750154331058,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00024153437692913822,"input_cache_write":0.0,"max_prompt_cost":966.137507716553,"max_completion_cost":2473.312019754376,"max_cost":3130.285525001632},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.2:batch","name":"OpenAI: GPT-5.2 (batch)","created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":9.625e-7,"completion":7.7e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":9.625e-8,"input_cache_write":0.0,"max_prompt_cost":0.38500000000000006,"max_completion_cost":0.9856000000000001,"max_cost":1.2474000000000003},"sats_pricing":{"prompt":0.0012076718846456911,"completion":0.009661375077165529,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00012076718846456911,"input_cache_write":0.0,"max_prompt_cost":483.0687538582765,"max_completion_cost":1236.656009877188,"max_cost":1565.142762500816},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.2-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"devstral-2512","name":"Mistral: Devstral 2 2512","created":1765285419,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","context_length":262144,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.11534336,"max_completion_cost":0.46137300000000003,"max_cost":0.48444176000000005},"sats_pricing":{"prompt":0.0005520785758380303,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":144.7240861844846,"max_completion_cost":578.8957926593625,"max_cost":607.8407203119747},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/devstral-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"relace-search","name":"Relace: Relace Search","created":1765213560,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":0.4224,"max_cost":0.5632},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.004140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":353.33028853633937,"max_completion_cost":529.9954328045089,"max_cost":706.6605770726787},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"relace/relace-search-20251208","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.6v","name":"Z.ai: GLM 4.6V","created":1765207462,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","context_length":131072,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.05e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.03244032,"max_cost":0.06488064},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.001242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007591080417772915,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":40.703649239386294,"max_cost":81.40729847877259},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.6-20251208","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","created":1764878934,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":0.55,"max_completion_cost":1.4080000000000001,"max_cost":1.7820000000000003},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0,"max_prompt_cost":690.0982197975378,"max_completion_cost":1766.6514426816968,"max_cost":2235.9182321440226},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-codex-max-20251204","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"nova-2-lite-v1","name":"Amazon: Nova 2 Lite","created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","context_length":1000000,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.33,"max_completion_cost":0.18022125000000003,"max_cost":0.48859470000000005},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":414.0589318785227,"max_completion_cost":226.1279341721582,"max_cost":613.0515139500219},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65535,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-2-lite-v1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","created":1764681735,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.0461373,"max_cost":0.05767168},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0,"max_prompt_cost":72.3620430922423,"max_completion_cost":57.88957926593625,"max_cost":72.3620430922423},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-14b-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":1.65e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-8,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.034602975,"max_cost":0.04325376},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.00020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00002070294659392613,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":43.417184449452186,"max_cost":54.27153231918172},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-8b-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":1.1e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.01441792,"max_completion_cost":0.011534270000000001,"max_cost":0.01441792},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00013801964395950757,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.0,"max_prompt_cost":18.090510773060576,"max_completion_cost":14.472325806662084,"max_cost":18.090510773060576},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-3b-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-large-2512","name":"Mistral: Mistral Large 3 2512","created":1764624472,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.34602975,"max_cost":0.3748657},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.0020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":434.1718444945219,"max_cost":470.353004060287},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.000027500000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":6.875000000000001e-6,"max_prompt_cost":1.1,"max_completion_cost":1.7600000000000002,"max_cost":2.5080000000000005},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.034504910989876895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.008626227747469224,"max_prompt_cost":1380.1964395950756,"max_completion_cost":2208.314303352121,"max_cost":3146.8478822767725},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-opus-20251124","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":3.4375000000000005e-6,"max_prompt_cost":0.55,"max_completion_cost":0.8800000000000001,"max_cost":1.2540000000000002},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.017252455494938448,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.004313113873734612,"max_prompt_cost":690.0982197975378,"max_completion_cost":1104.1571516760605,"max_cost":1573.4239411383862},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-opus-20251124","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-3-pro-image-preview","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","created":1763653797,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":0.0000132,"request":0.0,"image":2.2e-6,"image_output":0.000132,"web_search":0.015400000000000002,"internal_reasoning":0.0000132,"input_cache_read":2.2e-7,"input_cache_write":4.125e-7,"max_prompt_cost":0.1441792,"max_completion_cost":0.4325376,"max_cost":0.5046272},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.016562357275140906,"request":0.001,"image":0.002760392879190151,"image_output":0.16562357275140907,"web_search":19.32275015433106,"internal_reasoning":0.016562357275140906,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0005175736648481533,"max_prompt_cost":180.90510773060575,"max_completion_cost":542.7153231918172,"max_cost":633.1678770571201},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-pro-image-preview-20251120","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gpt-5.1","name":"OpenAI: GPT-5.1","created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":0.55,"max_completion_cost":1.4080000000000001,"max_cost":1.7820000000000003},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0,"max_prompt_cost":690.0982197975378,"max_completion_cost":1766.6514426816968,"max_cost":2235.9182321440226},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.1:batch","name":"OpenAI: GPT-5.1 (batch)","created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.875000000000001e-7,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":6.875e-8,"input_cache_write":0.0,"max_prompt_cost":0.275,"max_completion_cost":0.7040000000000001,"max_cost":0.8910000000000001},"sats_pricing":{"prompt":0.0008626227747469223,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00008626227747469223,"input_cache_write":0.0,"max_prompt_cost":345.0491098987689,"max_completion_cost":883.3257213408484,"max_cost":1117.9591160720113},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","created":1763060298,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.4300000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":0.55,"max_completion_cost":1.4080000000000001,"max_cost":1.7820000000000003},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00017942553714735983,"input_cache_write":0.0,"max_prompt_cost":690.0982197975378,"max_completion_cost":1766.6514426816968,"max_cost":2235.9182321440226},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-codex-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","created":1763057820,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.11,"max_completion_cost":0.2816,"max_cost":0.35640000000000005},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":138.01964395950756,"max_completion_cost":353.33028853633937,"max_cost":447.18364642880454},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5.1-codex-mini-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.270336,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":339.1970769948858,"max_cost":474.8759077928401},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2-thinking-20251106","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true},"image_pricing":null},{"id":"nova-premier-v1","name":"Amazon: Nova Premier 1.0","created":1761950332,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000013750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.875000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":2.7500000000000004,"max_completion_cost":0.44000000000000006,"max_cost":3.1020000000000003},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.017252455494938448,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0008626227747469223,"input_cache_write":0.0,"max_prompt_cost":3450.4910989876894,"max_completion_cost":552.0785758380302,"max_cost":3892.1539596581133},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-premier-v1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"sonar-pro-search","name":"Perplexity: Sonar Pro Search","created":1761854366,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0198,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.66,"max_completion_cost":0.132,"max_cost":0.7656000000000001},"sats_pricing":{"prompt":0.004140589318785227,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":24.84353591271136,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":828.1178637570454,"max_completion_cost":165.62357275140906,"max_cost":960.6167219581725},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-pro-search","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","created":1761835144,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","context_length":32768,"architecture":{"modality":"text+file+audio->text","input_modalities":["text","audio","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.00360448,"max_completion_cost":0.008650620000000001,"max_cost":0.009371560000000001},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000013801964395950756,"input_cache_write":0.0,"max_prompt_cost":4.522627693265144,"max_completion_cost":10.854140840263595,"max_cost":11.758721586774206},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/voxtral-small-24b-2507","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","created":1761752836,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.01081344,"max_completion_cost":0.02162688,"max_cost":0.0270336},"sats_pricing":{"prompt":0.00010351473296963067,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000051757366484815334,"input_cache_write":0.0,"max_prompt_cost":13.56788307979543,"max_completion_cost":27.13576615959086,"max_cost":33.919707699488576},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-safeguard-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["file","image","text"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":8.8e-6,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":1.1,"max_completion_cost":0.2816,"max_cost":1.0296},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.011041571516760605,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":1380.1964395950756,"max_completion_cost":353.33028853633937,"max_cost":1291.8638674609908},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-image-mini","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":5.5e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":6.875000000000001e-7,"max_prompt_cost":0.11,"max_completion_cost":0.17600000000000002,"max_cost":0.2508},"sats_pricing":{"prompt":0.0006900982197975378,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0008626227747469223,"max_prompt_cost":138.01964395950756,"max_completion_cost":220.8314303352121,"max_cost":314.68478822767725},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-haiku-20251001","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gpt-5-image","name":"OpenAI: GPT-5 Image","created":1760447986,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000011000000000000001,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.000044000000000000006,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":4.4,"max_completion_cost":1.4080000000000001,"max_cost":4.4},"sats_pricing":{"prompt":0.013801964395950756,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.055207857583803026,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0017252455494938446,"input_cache_write":0.0,"max_prompt_cost":5520.7857583803025,"max_completion_cost":1766.6514426816968,"max_cost":5520.7857583803025},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-image","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-2.5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","created":1759870431,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","context_length":32768,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":3.3e-7,"image_output":0.000033,"web_search":0.015400000000000002,"internal_reasoning":2.7500000000000004e-6,"input_cache_read":3.3e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.01081344,"max_completion_cost":0.022528000000000003,"max_cost":0.030638080000000005},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.003450491098987689,"request":0.001,"image":0.00041405893187852267,"image_output":0.04140589318785227,"web_search":19.32275015433106,"internal_reasoning":0.003450491098987689,"input_cache_read":0.00004140589318785226,"input_cache_write":0.00011501636996625625,"max_prompt_cost":13.56788307979543,"max_completion_cost":28.26642308290715,"max_cost":38.442335392753726},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash-image","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","created":1759794479,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.19e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.083623936,"max_completion_cost":0.2595219,"max_cost":0.267884485},"sats_pricing":{"prompt":0.00040025696748257185,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":104.92496248375132,"max_completion_cost":325.6283657972266,"max_cost":336.1211021997822},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-30b-a3b-thinking","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.01081344,"max_cost":0.05136384},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":13.56788307979543,"max_cost":64.4474446290283},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-30b-a3b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-5-pro","name":"OpenAI: GPT-5 Pro","created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000165,"completion":0.000132,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.6000000000000005,"max_completion_cost":16.896,"max_cost":21.384},"sats_pricing":{"prompt":0.020702946593926134,"completion":0.16562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":8281.178637570454,"max_completion_cost":21199.81731218036,"max_cost":26831.01878572827},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-pro-2025-10-06","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"},"image_pricing":null},{"id":"gpt-5-pro:batch","name":"OpenAI: GPT-5 Pro (batch)","created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-6,"completion":0.000066,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.3000000000000003,"max_completion_cost":8.448,"max_cost":10.692},"sats_pricing":{"prompt":0.010351473296963067,"completion":0.08281178637570454,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4140.589318785227,"max_completion_cost":10599.90865609018,"max_cost":13415.509392864134},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-pro-2025-10-06","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"},"image_pricing":null},{"id":"claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.65e-6,"completion":8.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":2.0625e-6,"max_prompt_cost":1.6500000000000001,"max_completion_cost":0.528,"max_cost":2.0724},"sats_pricing":{"prompt":0.0020702946593926133,"completion":0.010351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0025878683242407667,"max_prompt_cost":2070.2946593926135,"max_completion_cost":662.4942910056362,"max_cost":2600.2900921971222},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":2.97e-7,"completion":4.51e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.048660480000000006,"max_completion_cost":0.066502656,"max_cost":0.07136870399999999},"sats_pricing":{"prompt":0.00037265303869067043,"completion":0.000565880540233981,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":61.05547385907944,"max_completion_cost":83.44248094074189,"max_cost":89.54802832664983},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v3.2-exp","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":5.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.04325376,"max_completion_cost":0.0648802,"max_cost":0.06920584},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020702946593926133,"input_cache_write":0.0,"max_prompt_cost":54.27153231918172,"max_completion_cost":81.40674640019674,"max_cost":86.83423087926042},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/cydonia-24b-v4.1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"relace-apply-3","name":"Relace: Relace Apply 3","created":1758891572,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9.35e-7,"completion":1.3750000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.23936000000000002,"max_completion_cost":0.17600000000000002,"max_cost":0.29568000000000005},"sats_pricing":{"prompt":0.0011731669736558142,"completion":0.0017252455494938446,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":300.3307452558884,"max_completion_cost":220.8314303352121,"max_cost":370.99680296315637},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"relace/relace-apply-3","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.3100000000000002e-7,"completion":2.0900000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.030277632000000002,"max_completion_cost":0.06848512000000001,"max_cost":0.09119334400000001},"sats_pricing":{"prompt":0.0002898412523149659,"completion":0.002622373235230644,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":37.99007262342721,"max_completion_cost":85.92992617203774,"max_cost":114.42248063960814},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-235b-a22b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":2.97e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.048660480000000006,"max_completion_cost":0.1622016,"max_cost":0.167067648},"sats_pricing":{"prompt":0.00037265303869067043,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":61.05547385907944,"max_completion_cost":203.51824619693144,"max_cost":209.6237935828394},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v3.1-terminus","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.1450000000000002e-7,"completion":1.0725000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.29e-8,"input_cache_write":2.6812500000000003e-7,"max_prompt_cost":0.21450000000000002,"max_completion_cost":0.07028736000000001,"max_cost":0.27072988800000003},"sats_pricing":{"prompt":0.0002691383057210397,"completion":0.0013456915286051987,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00005382766114420794,"input_cache_write":0.00033642288215129967,"max_prompt_cost":269.1383057210397,"max_completion_cost":88.1912400186703,"max_cost":339.691297735976},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-flash","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.17301504,"max_completion_cost":0.270336,"max_cost":0.37847040000000004},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.003450491098987689,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":217.0861292767269,"max_completion_cost":339.1970769948858,"max_cost":474.8759077928401},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2-0905","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"hermes-4-405b","name":"Nous: Hermes 4 405B","created":1756235463,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.3892812,"max_cost":0.4037},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.004140589318785227,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":488.4404784011804,"max_cost":506.53209333139273},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nousresearch/hermes-4-405b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":2.75e-7,"completion":1.0450000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.4300000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":0.045056,"max_completion_cost":0.15409152000000004,"max_cost":0.15859712000000004},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.001311186617615322,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00017942553714735983,"input_cache_write":0.0,"max_prompt_cost":56.53284616581429,"max_completion_cost":193.34233388708492,"max_cost":198.99561850366635},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3.1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.2306854,"max_cost":0.24222000000000002},"sats_pricing":{"prompt":0.0005520785758380303,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":72.3620430922423,"max_completion_cost":289.4465161332417,"max_cost":303.91925599883564},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-5","name":"OpenAI: GPT-5","created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-7,"input_cache_write":0.0,"max_prompt_cost":0.55,"max_completion_cost":1.4080000000000001,"max_cost":1.7820000000000003},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0,"max_prompt_cost":690.0982197975378,"max_completion_cost":1766.6514426816968,"max_cost":2235.9182321440226},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5:batch","name":"OpenAI: GPT-5 (batch)","created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.875000000000001e-7,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":6.875e-8,"input_cache_write":0.0,"max_prompt_cost":0.275,"max_completion_cost":0.7040000000000001,"max_cost":0.8910000000000001},"sats_pricing":{"prompt":0.0008626227747469223,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00008626227747469223,"input_cache_write":0.0,"max_prompt_cost":345.0491098987689,"max_completion_cost":883.3257213408484,"max_cost":1117.9591160720113},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5-mini","name":"OpenAI: GPT-5 Mini","created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.75e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.11,"max_completion_cost":0.2816,"max_cost":0.35640000000000005},"sats_pricing":{"prompt":0.0003450491098987689,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0,"max_prompt_cost":138.01964395950756,"max_completion_cost":353.33028853633937,"max_cost":447.18364642880454},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-mini-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5-mini:batch","name":"OpenAI: GPT-5 Mini (batch)","created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.375e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-8,"input_cache_write":0.0,"max_prompt_cost":0.055,"max_completion_cost":0.1408,"max_cost":0.17820000000000003},"sats_pricing":{"prompt":0.00017252455494938445,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000017252455494938446,"input_cache_write":0.0,"max_prompt_cost":69.00982197975378,"max_completion_cost":176.66514426816968,"max_cost":223.59182321440227},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-mini-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5-nano","name":"OpenAI: GPT-5 Nano","created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":4.4e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.022000000000000002,"max_completion_cost":0.05632,"max_cost":0.07128000000000001},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":6.900982197975378e-6,"input_cache_write":0.0,"max_prompt_cost":27.603928791901513,"max_completion_cost":70.66605770726787,"max_cost":89.4367292857609},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-nano-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5-nano:batch","name":"OpenAI: GPT-5 Nano (batch)","created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.75e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.7500000000000002e-9,"input_cache_write":0.0,"max_prompt_cost":0.011000000000000001,"max_completion_cost":0.02816,"max_cost":0.035640000000000005},"sats_pricing":{"prompt":0.00003450491098987689,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":3.450491098987689e-6,"input_cache_write":0.0,"max_prompt_cost":13.801964395950757,"max_completion_cost":35.333028853633934,"max_cost":44.71836464288045},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-5-nano-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-oss-120b:batch","name":"OpenAI: gpt-oss-120b (batch)","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.256e-8,"completion":1.4960000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00426770432,"max_completion_cost":0.017647414400000002,"max_cost":0.018074210880000004},"sats_pricing":{"prompt":0.000040853814612014234,"completion":0.0001877067157849303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.35479118882593,"max_completion_cost":22.142635020853515,"max_cost":22.678146822787802},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-120b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-oss-20b:batch","name":"OpenAI: gpt-oss-20b (batch)","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.64e-8,"completion":1.2320000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0034603008,"max_completion_cost":0.014533164800000001,"max_cost":0.014879216},"sats_pricing":{"prompt":0.000033124714550281815,"completion":0.00015458200123464848,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.341722585534538,"max_completion_cost":18.235111193644073,"max_cost":18.669309951969165},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-oss-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":0.0000165,"completion":0.0000825,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.65e-6,"input_cache_write":0.000020625,"max_prompt_cost":3.3000000000000003,"max_completion_cost":2.64,"max_cost":5.412000000000001},"sats_pricing":{"prompt":0.020702946593926134,"completion":0.10351473296963067,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0020702946593926133,"input_cache_write":0.025878683242407666,"max_prompt_cost":4140.589318785227,"max_completion_cost":3312.4714550281815,"max_cost":6790.566482807772},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.1-opus-20250805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":8.25e-6,"completion":0.00004125,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":8.25e-7,"input_cache_write":0.0000103125,"max_prompt_cost":1.6500000000000001,"max_completion_cost":1.32,"max_cost":2.7060000000000004},"sats_pricing":{"prompt":0.010351473296963067,"completion":0.05175736648481533,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0010351473296963066,"input_cache_write":0.012939341621203833,"max_prompt_cost":2070.2946593926135,"max_completion_cost":1656.2357275140907,"max_cost":3395.283241403886},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.1-opus-20250805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"codestral-2508","name":"Mistral: Codestral 2508","created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","context_length":256000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.08448,"max_completion_cost":0.20275200000000002,"max_cost":0.219648},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.001242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":105.9990865609018,"max_completion_cost":254.39780774616432,"max_cost":275.5976250583447},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":204800,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/codestral-2508","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.07785657,"max_cost":0.08074022},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":97.68850973916797,"max_cost":101.30669470556646},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-30b-a3b-instruct-2507","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.5","name":"Z.ai: GLM 4.5","created":1753471347,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.21e-7,"input_cache_write":0.0,"max_prompt_cost":0.08650752,"max_completion_cost":0.23789568,"max_cost":0.25952256},"sats_pricing":{"prompt":0.0008281178637570453,"completion":0.0030364321671091663,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001518216083554583,"input_cache_write":0.0,"max_prompt_cost":108.54306463836345,"max_completion_cost":298.49342775549945,"max_cost":325.62919391509035},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.5","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"glm-4.5-air","name":"Z.ai: GLM 4.5 Air","created":1753471258,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.4300000000000002e-7,"completion":9.35e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.018743296000000003,"max_completion_cost":0.09191424000000001,"max_cost":0.09660006400000001},"sats_pricing":{"prompt":0.00017942553714735983,"completion":0.0011731669736558142,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0,"max_prompt_cost":23.517664004978748,"max_completion_cost":115.32700617826116,"max_cost":121.20642217950585},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.5-air","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.08650752,"max_completion_cost":0.0720896,"max_cost":0.13697024000000002},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":108.54306463836345,"max_completion_cost":90.45255386530287,"max_cost":171.85985234407548},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-480b-a35b-07-25","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.01408,"max_completion_cost":0.00045056,"max_cost":0.01430528},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":17.666514426816967,"max_completion_cost":0.565328461658143,"max_cost":17.949178657646037},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance/ui-tars-1.5-7b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":4.4e-7,"request":0.0,"image":1.1e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":4.4e-7,"input_cache_read":1.1000000000000001e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.11534336,"max_completion_cost":0.0288354,"max_cost":0.13696991},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0005520785758380303,"request":0.001,"image":0.00013801964395950757,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.0005520785758380303,"input_cache_read":0.000013801964395950756,"input_cache_write":0.00011501636996625625,"max_prompt_cost":144.7240861844846,"max_completion_cost":36.18046946754531,"max_cost":171.85943828514357},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash-lite","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.5400000000000003e-7,"completion":8.8e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.020185088000000004,"max_completion_cost":0.10380832000000001,"max_cost":0.10582695200000002},"sats_pricing":{"prompt":0.0001932275015433106,"completion":0.0011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":25.326715082284807,"max_completion_cost":130.2507942403148,"max_cost":132.78362033054452},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-235b-a22b-07-25","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2","name":"MoonshotAI: Kimi K2 0711","created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.270000000000001e-7,"completion":2.5300000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.08218214400000001,"max_completion_cost":0.24870912000000003,"max_cost":0.26925465600000004},"sats_pricing":{"prompt":0.0007867119705691931,"completion":0.003174451811068674,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":103.11591140644528,"max_completion_cost":312.06131083529493,"max_cost":337.84028868690626},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","created":1752094966,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":9.9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02816,"max_completion_cost":0.00811008,"max_cost":0.03446784},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.001242176795635568,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":35.333028853633934,"max_completion_cost":10.175912309846574,"max_cost":43.24762731684793},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"venice/uncensored","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","created":1751987664,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5400000000000003e-7,"completion":6.270000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.020185088000000004,"max_completion_cost":0.07396342800000001,"max_cost":0.07598206000000002},"sats_pricing":{"prompt":0.0001932275015433106,"completion":0.0007867119705691931,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":25.326715082284807,"max_completion_cost":92.8036908962243,"max_cost":95.33651698645403},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hunyuan-a13b-instruct","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"morph-v3-large","name":"Morph: Morph V3 Large","created":1751910858,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9.9e-7,"completion":2.0900000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.25952256,"max_completion_cost":0.27394048000000004,"max_cost":0.40370176},"sats_pricing":{"prompt":0.001242176795635568,"completion":0.002622373235230644,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":325.62919391509035,"max_completion_cost":343.71970468815096,"max_cost":506.5343016456961},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"morph/morph-v3-large","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"morph-v3-fast","name":"Morph: Morph V3 Fast","created":1751910002,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":1.32e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.23068672,"max_completion_cost":0.17301504,"max_cost":0.2883584},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.0016562357275140907,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":289.4481723689692,"max_completion_cost":217.0861292767269,"max_cost":361.8102154612115},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"morph/morph-v3-fast","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.00360448,"max_cost":0.012812800000000001},"sats_pricing":{"prompt":0.00010351473296963067,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.249885820112725,"max_completion_cost":4.522627693265144,"max_cost":16.07652812840344},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-3.2-24b-instruct-2506","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m1","name":"MiniMax: MiniMax M1","created":1750200414,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.605,"max_completion_cost":0.09680000000000001,"max_cost":0.6776},"sats_pricing":{"prompt":0.0007591080417772916,"completion":0.0030364321671091663,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":759.1080417772915,"max_completion_cost":121.45728668436665,"max_cost":850.2010067905665},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":40000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.3e-7,"completion":2.7500000000000004e-6,"request":0.0,"image":3.3e-7,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":2.7500000000000004e-6,"input_cache_read":3.3e-8,"input_cache_write":9.166666666666664e-8,"max_prompt_cost":0.34603008,"max_completion_cost":0.18022125000000003,"max_cost":0.50462478},"sats_pricing":{"prompt":0.00041405893187852267,"completion":0.003450491098987689,"request":0.001,"image":0.00041405893187852267,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.003450491098987689,"input_cache_read":0.00004140589318785226,"input_cache_write":0.00011501636996625625,"max_prompt_cost":434.1722585534538,"max_completion_cost":226.1279341721582,"max_cost":633.164840624953},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","created":1750169544,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":1.3750000000000002e-6,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.000011000000000000001,"input_cache_read":1.375e-7,"input_cache_write":4.125e-7,"max_prompt_cost":1.4417920000000002,"max_completion_cost":0.7208960000000001,"max_cost":2.072576},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.013801964395950756,"request":0.001,"image":0.0017252455494938446,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.013801964395950756,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0005175736648481533,"max_prompt_cost":1809.0510773060576,"max_completion_cost":904.5255386530288,"max_cost":2600.5109236274575},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-pro","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"o3-pro","name":"OpenAI: o3 Pro","created":1749598352,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","file","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000022000000000000003,"completion":0.00008800000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.4,"max_completion_cost":8.8,"max_cost":11.0},"sats_pricing":{"prompt":0.027603928791901513,"completion":0.11041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5520.7857583803025,"max_completion_cost":11041.571516760605,"max_cost":13801.964395950754},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o3-pro-2025-06-10","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","created":1749137257,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio->text","input_modalities":["file","image","text","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":0.000011000000000000001,"request":0.0,"image":1.3750000000000002e-6,"image_output":0.0,"web_search":0.015400000000000002,"internal_reasoning":0.000011000000000000001,"input_cache_read":1.375e-7,"input_cache_write":4.125e-7,"max_prompt_cost":1.4417920000000002,"max_completion_cost":0.7208960000000001,"max_cost":2.072576},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.013801964395950756,"request":0.001,"image":0.0017252455494938446,"image_output":0.0,"web_search":19.32275015433106,"internal_reasoning":0.013801964395950756,"input_cache_read":0.00017252455494938445,"input_cache_write":0.0005175736648481533,"max_prompt_cost":1809.0510773060576,"max_completion_cost":904.5255386530288,"max_cost":2600.5109236274575},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-pro-preview-06-05","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"mistral-medium-3","name":"Mistral: Mistral Medium 3","created":1746627341,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.4000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.05767168,"max_completion_cost":0.2306854,"max_cost":0.24222000000000002},"sats_pricing":{"prompt":0.0005520785758380303,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000055207857583803025,"input_cache_write":0.0,"max_prompt_cost":72.3620430922423,"max_completion_cost":289.4465161332417,"max_cost":303.91925599883564},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","context_length":163840,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.9800000000000003e-7,"completion":1.9800000000000003e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.03244032,"max_completion_cost":0.0032440320000000004,"max_cost":0.03244032},"sats_pricing":{"prompt":0.0002484353591271136,"completion":0.0002484353591271136,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":40.703649239386294,"max_completion_cost":4.070364923938629,"max_cost":40.703649239386294},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-guard-4-12b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"o3","name":"OpenAI: o3","created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":8.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.44,"max_completion_cost":0.88,"max_cost":1.1},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":552.0785758380302,"max_completion_cost":1104.1571516760605,"max_cost":1380.1964395950756},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o3-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"o3:batch","name":"OpenAI: o3 (batch)","created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.22,"max_completion_cost":0.44,"max_cost":0.55},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.005520785758380302,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":276.0392879190151,"max_completion_cost":552.0785758380302,"max_cost":690.0982197975378},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o3-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"o4-mini:batch","name":"OpenAI: o4 Mini (batch)","created":1744820942,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.5125e-7,"input_cache_write":0.0,"max_prompt_cost":0.12100000000000001,"max_completion_cost":0.24200000000000002,"max_cost":0.30250000000000005},"sats_pricing":{"prompt":0.0007591080417772916,"completion":0.0030364321671091663,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0001897770104443229,"input_cache_write":0.0,"max_prompt_cost":151.82160835545832,"max_completion_cost":303.64321671091665,"max_cost":379.5540208886458},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o4-mini-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gpt-4.1","name":"OpenAI: GPT-4.1","created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":8.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-7,"input_cache_write":0.0,"max_prompt_cost":2.3046672,"max_completion_cost":0.2883584,"max_cost":2.520936},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0006900982197975378,"input_cache_write":0.0,"max_prompt_cost":2891.7213308105015,"max_completion_cost":361.8102154612115,"max_cost":3163.07899240641},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1:batch","name":"OpenAI: GPT-4.1 (batch)","created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":1.1523336,"max_completion_cost":0.1441792,"max_cost":1.260468},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.005520785758380302,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":1445.8606654052508,"max_completion_cost":180.90510773060575,"max_cost":1581.539496203205},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.4e-7,"completion":1.76e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.1e-7,"input_cache_write":0.0,"max_prompt_cost":0.46093344,"max_completion_cost":0.05767168,"max_cost":0.5041872000000001},"sats_pricing":{"prompt":0.0005520785758380303,"completion":0.002208314303352121,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00013801964395950757,"input_cache_write":0.0,"max_prompt_cost":578.3442661621003,"max_completion_cost":72.3620430922423,"max_cost":632.6157984812821},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1-mini:batch","name":"OpenAI: GPT-4.1 Mini (batch)","created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":8.8e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":5.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.23046672,"max_completion_cost":0.02883584,"max_cost":0.25209360000000003},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00006900982197975378,"input_cache_write":0.0,"max_prompt_cost":289.17213308105016,"max_completion_cost":36.18102154612115,"max_cost":316.30789924064106},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":3.3e-8,"input_cache_write":0.0,"max_prompt_cost":0.11523336,"max_completion_cost":0.41483992000000003,"max_cost":0.4263633},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.00004140589318785226,"input_cache_write":0.0,"max_prompt_cost":144.58606654052508,"max_completion_cost":520.50961871446,"max_cost":534.96828057637},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":942818,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1-nano:batch","name":"OpenAI: GPT-4.1 Nano (batch)","created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.5e-8,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":1.375e-8,"input_cache_write":0.0,"max_prompt_cost":0.05761668,"max_completion_cost":0.00720896,"max_cost":0.06302340000000001},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000017252455494938446,"input_cache_write":0.0,"max_prompt_cost":72.29303327026254,"max_completion_cost":9.045255386530288,"max_cost":79.07697481016027},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-4-maverick","name":"Meta: Llama 4 Maverick","created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","context_length":524288,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":3.85e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.87e-7,"input_cache_write":0.0,"max_prompt_cost":0.20185088,"max_completion_cost":0.0360448,"max_cost":0.22528000000000004},"sats_pricing":{"prompt":0.00048306875385827644,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002346333947311628,"input_cache_write":0.0,"max_prompt_cost":253.26715082284804,"max_completion_cost":45.22627693265144,"max_cost":282.6642308290715},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-4-maverick-17b-128e-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-4-scout","name":"Meta: Llama 4 Scout","created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","context_length":1310720,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0360448,"max_completion_cost":0.00540672,"max_cost":0.03964928000000001},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":45.22627693265144,"max_completion_cost":6.783941539897715,"max_cost":49.74890462591659},"per_request_limits":null,"top_provider":{"context_length":327680,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-4-scout-17b-16e-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":3.19e-7,"completion":1.2540000000000002e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.21e-7,"input_cache_write":0.0,"max_prompt_cost":0.040832,"max_completion_cost":0.14446080000000003,"max_cost":0.14854400000000004},"sats_pricing":{"prompt":0.00040025696748257185,"completion":0.0015734239411383862,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001518216083554583,"input_cache_write":0.0,"max_prompt_cost":51.2328918377692,"max_completion_cost":181.25843801914212,"max_cost":186.38172720291905},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3-0324","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3.8610000000000005e-7,"completion":6.105e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.04942080000000001,"max_completion_cost":0.0625152,"max_cost":0.07239936000000001},"sats_pricing":{"prompt":0.00048444895029787154,"completion":0.0007660090239752669,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":62.00946563812756,"max_completion_cost":78.43932405506733,"max_cost":90.84121718269286},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-3.1-24b-instruct-2503","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-12b-it","name":"Google: Gemma 3 12B","created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":5.5e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.00270336,"max_cost":0.0090112},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.00020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.045255386530288,"max_completion_cost":3.3919707699488577,"max_cost":11.30656923316286},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-3-12b-it","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"command-a","name":"Cohere: Command A","created":1741894342,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.7040000000000001,"max_completion_cost":0.09011200000000001,"max_cost":0.771584},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":883.3257213408484,"max_completion_cost":113.0656923316286,"max_cost":968.1249905895698},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-a-03-2025","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"reka-flash-3","name":"Reka Flash 3","created":1741812813,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.012976040000000001,"max_cost":0.013696980000000001},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.045255386530288,"max_completion_cost":16.28134928003935,"max_cost":17.18593002654996},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"rekaai/reka-flash-3","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":8.8e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.01982464,"max_completion_cost":0.025952080000000002,"max_cost":0.027934665000000004},"sats_pricing":{"prompt":0.0007591080417772916,"completion":0.0011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003450491098987689,"input_cache_write":0.0,"max_prompt_cost":24.87445231295829,"max_completion_cost":32.5626985600787,"max_cost":35.050295612982886},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/skyfall-36b-v2","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","created":1741313308,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":2.2e-6,"completion":8.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":1.01376,"max_cost":1.04192},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":353.33028853633937,"max_completion_cost":1271.9890387308214,"max_cost":1307.3220675844555},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-reasoning-pro","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"sonar-pro","name":"Perplexity: Sonar Pro","created":1741312423,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.66,"max_completion_cost":0.132,"max_cost":0.7656000000000001},"sats_pricing":{"prompt":0.004140589318785227,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":828.1178637570454,"max_completion_cost":165.62357275140906,"max_cost":960.6167219581725},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-pro","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"sonar-deep-research","name":"Perplexity: Sonar Deep Research","created":1741311246,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":2.2e-6,"completion":8.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":3.3e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":1.01376,"max_cost":1.04192},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.004140589318785227,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":353.33028853633937,"max_completion_cost":1271.9890387308214,"max_cost":1307.3220675844555},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-deep-research","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"mistral-saba","name":"Mistral: Saba","created":1739803239,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","context_length":32768,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.017301240000000002,"max_cost":0.018743120000000002},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000027603928791901512,"input_cache_write":0.0,"max_prompt_cost":9.045255386530288,"max_completion_cost":21.70828168052719,"max_cost":23.51744317354841},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-saba-2502","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","created":1738696718,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":1.76e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02883584,"max_completion_cost":0.051904160000000005,"max_cost":0.054787920000000004},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.002208314303352121,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":36.18102154612115,"max_completion_cost":65.1253971201574,"max_cost":68.74372010619985},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-rp-llama-3.1-8b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-plus","name":"Qwen: Qwen-Plus","created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.8600000000000005e-7,"completion":8.580000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.720000000000001e-8,"input_cache_write":3.575e-7,"max_prompt_cost":0.28600000000000003,"max_completion_cost":0.028114944000000003,"max_cost":0.30474329600000005},"sats_pricing":{"prompt":0.00035885107429471967,"completion":0.0010765532228841589,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007177021485894394,"input_cache_write":0.00044856384286839955,"max_prompt_cost":358.85107429471964,"max_completion_cost":35.27649600746812,"max_cost":382.3687382996984},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-plus-2025-01-25","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"o3-mini:batch","name":"OpenAI: o3 Mini (batch)","created":1738351721,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","context_length":200000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6.05e-7,"completion":2.42e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":3.025e-7,"input_cache_write":0.0,"max_prompt_cost":0.12100000000000001,"max_completion_cost":0.24200000000000002,"max_cost":0.30250000000000005},"sats_pricing":{"prompt":0.0007591080417772916,"completion":0.0030364321671091663,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0003795540208886458,"input_cache_write":0.0,"max_prompt_cost":151.82160835545832,"max_completion_cost":303.64321671091665,"max_cost":379.5540208886458},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/o3-mini-2025-01-31","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"sonar","name":"Perplexity: Sonar","created":1738013808,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","context_length":127072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0055000000000000005,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.13977920000000002,"max_completion_cost":0.1258004,"max_cost":0.13977920000000002},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":6.900982197975378,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":175.38432197222545,"max_completion_cost":157.84478561785122,"max_cost":175.38432197222545},"per_request_limits":null,"top_provider":{"context_length":127072,"max_completion_tokens":114364,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-01","name":"MiniMax: MiniMax-01","created":1736915462,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...","context_length":1000192,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":1.21e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.22004224,"max_completion_cost":1.0892081200000001,"max_cost":1.11121252},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0015182160835545831,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":276.09228746229553,"max_completion_cost":1366.6556083654962,"max_cost":1394.265057943156},"per_request_limits":null,"top_provider":{"context_length":1000192,"max_completion_tokens":900172,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-01","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"phi-4","name":"Microsoft: Phi 4","created":1736489872,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.700000000000001e-8,"completion":1.5400000000000003e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0012615680000000002,"max_completion_cost":0.0022707300000000003,"max_cost":0.0023969330000000004},"sats_pricing":{"prompt":0.0000966137507716553,"completion":0.0001932275015433106,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.5829196926428004,"max_completion_cost":2.849139510256115,"max_cost":3.007489447770858},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"microsoft/phi-4","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-chat","name":"DeepSeek: DeepSeek V3","created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":2.8314000000000003e-7,"completion":1.1315700000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.0800000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.036241920000000004,"max_completion_cost":0.018105120000000002,"max_cost":0.04981680000000001},"sats_pricing":{"prompt":0.0003552625635517725,"completion":0.0014198080774114543,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003864550030866212,"input_cache_write":0.0,"max_prompt_cost":45.47360813462687,"max_completion_cost":22.71692923858327,"max_cost":62.50633635638179},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","created":1734158152,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":4.125e-8,"completion":1.65e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00528,"max_completion_cost":0.00066,"max_cost":0.005775000000000001},"sats_pricing":{"prompt":0.000051757366484815334,"completion":0.00020702946593926133,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.624942910056363,"max_completion_cost":0.8281178637570453,"max_cost":7.246031307874147},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r7b-12-2024","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nova-lite-v1","name":"Amazon: Nova Lite 1.0","created":1733437363,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":2.64e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.019799999999999998,"max_completion_cost":0.0013516799999999999,"max_cost":0.02081376},"sats_pricing":{"prompt":0.00008281178637570452,"completion":0.0003312471455028181,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":24.843535912711356,"max_completion_cost":1.6959853849744286,"max_cost":26.11552495144218},"per_request_limits":null,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-lite-v1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nova-micro-v1","name":"Amazon: Nova Micro 1.0","created":1733437237,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":3.850000000000001e-8,"completion":1.5400000000000003e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004928000000000001,"max_completion_cost":0.0007884800000000001,"max_cost":0.005519360000000001},"sats_pricing":{"prompt":0.00004830687538582765,"completion":0.0001932275015433106,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.18328004938594,"max_completion_cost":0.9893248079017503,"max_cost":6.925273655312252},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-micro-v1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nova-pro-v1","name":"Amazon: Nova Pro 1.0","created":1733436303,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":3.52e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.264,"max_completion_cost":0.0180224,"max_cost":0.2775168},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.004416628606704242,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":331.2471455028181,"max_completion_cost":22.61313846632572,"max_cost":348.20699935256243},"per_request_limits":null,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-pro-v1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0017252455494938446,"input_cache_write":0.0,"max_prompt_cost":441.6628606704242,"max_completion_cost":226.1313846632572,"max_cost":611.2613991678671},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-2024-11-20","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-large-2407","name":"Mistral Large 2407","created":1731978415,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","context_length":131072,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.2883584,"max_completion_cost":0.6920562,"max_cost":0.7497292},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":361.8102154612115,"max_completion_cost":868.339548399725,"max_cost":940.7032477276948},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-2407","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":7.260000000000001e-7,"completion":1.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.023789568000000004,"max_completion_cost":0.0324401,"max_cost":0.034819202},"sats_pricing":{"prompt":0.0009109296501327499,"completion":0.0013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":29.84934277554995,"max_completion_cost":40.70337320009837,"max_cost":43.68848966358339},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-coder-32b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","created":1731103448,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","context_length":1024000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":4.4e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.45056,"max_completion_cost":0.360448,"max_cost":0.45055999999999996},"sats_pricing":{"prompt":0.0005520785758380303,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":565.3284616581429,"max_completion_cost":452.26276932651433,"max_cost":565.3284616581428},"per_request_limits":null,"top_provider":{"context_length":1024000,"max_completion_tokens":819200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/unslopnemo-12b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"magnum-v4-72b","name":"Magnum v4 72B","created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":2.7500000000000004e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.09011200000000001,"max_completion_cost":0.022528000000000003,"max_cost":0.10137600000000002},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":113.0656923316286,"max_completion_cost":28.26642308290715,"max_cost":127.19890387308219},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthracite-org/magnum-v4-72b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","created":1729036800,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":1.1e-7,"completion":2.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00360448,"max_completion_cost":0.006488020000000001,"max_cost":0.0068484900000000005},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.00027603928791901513,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.522627693265144,"max_completion_cost":8.140674640019675,"max_cost":8.59296501327498},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-7b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":3.9600000000000005e-7,"completion":4.4e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.012976128000000002,"max_completion_cost":0.00720896,"max_cost":0.013697024000000002},"sats_pricing":{"prompt":0.0004968707182542272,"completion":0.0005520785758380303,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":16.281459695754517,"max_completion_cost":9.045255386530288,"max_cost":17.185985234407546},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-72b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"command-r-08-2024","name":"Cohere: Command R (08-2024)","created":1724976000,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02112,"max_completion_cost":0.00264,"max_cost":0.023100000000000002},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":26.49977164022545,"max_completion_cost":3.3124714550281813,"max_cost":28.984125231496588},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r-08-2024","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","created":1724976000,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.044000000000000004,"max_cost":0.385},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":441.6628606704242,"max_completion_cost":55.207857583803026,"max_cost":483.0687538582764},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r-plus-08-2024","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":9.35e-7,"completion":9.35e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.12255232,"max_completion_cost":0.01531904,"max_cost":0.12255232},"sats_pricing":{"prompt":0.0011731669736558142,"completion":0.0011731669736558142,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":153.76934157101488,"max_completion_cost":19.22116769637686,"max_cost":153.76934157101488},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sao10k/l3.1-euryale-70b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":4.4000000000000004e-8,"completion":5.5e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00036044800000000003,"max_completion_cost":0.00040546,"max_cost":0.00044154000000000003},"sats_pricing":{"prompt":0.000055207857583803025,"completion":0.00006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.4522627693265144,"max_completion_cost":0.5087404076347448,"max_cost":0.5540108508534634},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":7372,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sao10k/l3-lunaris-8b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0017252455494938446,"input_cache_write":0.0,"max_prompt_cost":441.6628606704242,"max_completion_cost":226.1313846632572,"max_cost":611.2613991678671},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-2024-08-06","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":7.920000000000001e-7,"completion":7.920000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.10380902400000001,"max_completion_cost":0.006488064000000001,"max_cost":0.10380902400000001},"sats_pricing":{"prompt":0.0009937414365084544,"completion":0.0009937414365084544,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":130.25167756603614,"max_completion_cost":8.140729847877259,"max_cost":130.25167756603614},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.1-70b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":5.5e-8,"completion":8.800000000000001e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.00720896,"max_completion_cost":0.010380832000000001,"max_cost":0.011101772000000001},"sats_pricing":{"prompt":0.00006900982197975378,"completion":0.00011041571516760605,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003450491098987689,"input_cache_write":0.0,"max_prompt_cost":9.045255386530288,"max_completion_cost":13.02507942403148,"max_cost":13.929660170542093},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.1-8b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-nemo","name":"Mistral: Mistral Nemo","created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3.19e-8,"completion":3.3e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0041811968,"max_completion_cost":0.000540672,"max_cost":0.0041992192},"sats_pricing":{"prompt":0.00004002569674825719,"completion":0.00004140589318785226,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.2462481241875665,"max_completion_cost":0.6783941539897714,"max_cost":5.268861262653892},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-nemo","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-mini","name":"OpenAI: GPT-4o-mini","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.02112,"max_completion_cost":0.01081344,"max_cost":0.029230080000000002},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":26.49977164022545,"max_completion_cost":13.56788307979543,"max_cost":36.67568395007203},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-mini","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":6.6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.02112,"max_completion_cost":0.01081344,"max_cost":0.029230080000000002},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010351473296963067,"input_cache_write":0.0,"max_prompt_cost":26.49977164022545,"max_completion_cost":13.56788307979543,"max_cost":36.67568395007203},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-mini-2024-07-18","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-mini:batch","name":"OpenAI: GPT-4o-mini (batch)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-8,"completion":3.3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":4.125e-8,"input_cache_write":0.0,"max_prompt_cost":0.01056,"max_completion_cost":0.00540672,"max_cost":0.014615040000000001},"sats_pricing":{"prompt":0.00010351473296963067,"completion":0.00041405893187852267,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.000051757366484815334,"input_cache_write":0.0,"max_prompt_cost":13.249885820112725,"max_completion_cost":6.783941539897715,"max_cost":18.337841975036014},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-mini","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o","name":"OpenAI: GPT-4o","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.7500000000000004e-6,"completion":0.000011000000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3750000000000002e-6,"input_cache_write":0.0,"max_prompt_cost":0.35200000000000004,"max_completion_cost":0.18022400000000002,"max_cost":0.48716800000000005},"sats_pricing":{"prompt":0.003450491098987689,"completion":0.013801964395950756,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0017252455494938446,"input_cache_write":0.0,"max_prompt_cost":441.6628606704242,"max_completion_cost":226.1313846632572,"max_cost":611.2613991678671},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.7040000000000001,"max_completion_cost":0.067584,"max_cost":0.749056},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":883.3257213408484,"max_completion_cost":84.79926924872144,"max_cost":939.8585675066627},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o-2024-05-13","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o:batch","name":"OpenAI: GPT-4o (batch)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3750000000000002e-6,"completion":5.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":6.875000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.17600000000000002,"max_completion_cost":0.09011200000000001,"max_cost":0.24358400000000002},"sats_pricing":{"prompt":0.0017252455494938446,"completion":0.006900982197975378,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0008626227747469223,"input_cache_write":0.0,"max_prompt_cost":220.8314303352121,"max_completion_cost":113.0656923316286,"max_cost":305.63069958393356},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4o","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","created":1713312000,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","context_length":65536,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.1441792,"max_completion_cost":0.3460248,"max_cost":0.37486240000000004},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":180.90510773060575,"max_completion_cost":434.16563361054375,"max_cost":470.34886347096824},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":52428,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mixtral-8x22b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4-turbo:batch","name":"OpenAI: GPT-4 Turbo (batch)","created":1712620800,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.500000000000001e-6,"completion":0.0000165,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.011000000000000001,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.7040000000000001,"max_completion_cost":0.067584,"max_cost":0.749056},"sats_pricing":{"prompt":0.006900982197975378,"completion":0.020702946593926134,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.801964395950757,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":883.3257213408484,"max_completion_cost":84.79926924872144,"max_cost":939.8585675066627},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4-turbo","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-large","name":"Mistral Large","created":1708905600,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","context_length":128000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.2e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2e-7,"input_cache_write":0.0,"max_prompt_cost":0.2816,"max_completion_cost":0.67584,"max_cost":0.73216},"sats_pricing":{"prompt":0.002760392879190151,"completion":0.008281178637570453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00027603928791901513,"input_cache_write":0.0,"max_prompt_cost":353.33028853633937,"max_completion_cost":847.9926924872144,"max_cost":918.6587501944823},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","context_length":4095,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.1e-6,"completion":2.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0045045,"max_completion_cost":0.008107,"max_cost":0.008558},"sats_pricing":{"prompt":0.0013801964395950756,"completion":0.002760392879190151,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.651904420141834,"max_completion_cost":10.172047759815706,"max_cost":10.737928300049687},"per_request_limits":null,"top_provider":{"context_length":4095,"max_completion_tokens":3685,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-3.5-turbo-0613","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","context_length":16385,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.3e-6,"completion":4.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0540705,"max_completion_cost":0.0180224,"max_cost":0.058576100000000006},"sats_pricing":{"prompt":0.004140589318785227,"completion":0.005520785758380302,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":67.84355598829593,"max_completion_cost":22.61313846632572,"max_cost":73.49684060487738},"per_request_limits":null,"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-3.5-turbo-16k","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"weaver","name":"Mancer: Weaver (alpha)","created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","context_length":8000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":4.4e-7,"completion":8.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00352,"max_completion_cost":0.00495,"max_cost":0.00583},"sats_pricing":{"prompt":0.0005520785758380303,"completion":0.0010351473296963066,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.416628606704242,"max_completion_cost":6.21088397817784,"max_cost":7.3150411298539},"per_request_limits":null,"top_provider":{"context_length":8000,"max_completion_tokens":6000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mancer/weaver","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"remm-slerp-l2-13b","name":"ReMM SLERP 13B","created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","context_length":6144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":3.85e-7,"completion":7.15e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00236544,"max_completion_cost":0.003953235,"max_cost":0.00419001},"sats_pricing":{"prompt":0.00048306875385827644,"completion":0.0008971276857367991,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.9679744237052503,"max_completion_cost":4.960218974438762,"max_cost":5.257306258061602},"per_request_limits":null,"top_provider":{"context_length":6144,"max_completion_tokens":5529,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"undi95/remm-slerp-l2-13b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mythomax-l2-13b","name":"MythoMax 13B","created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":8.800000000000001e-8,"completion":1.21e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00036044800000000003,"max_completion_cost":0.00044600600000000004,"max_cost":0.00048208600000000006},"sats_pricing":{"prompt":0.00011041571516760605,"completion":0.0001518216083554583,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.4522627693265144,"max_completion_cost":0.5596144483982194,"max_cost":0.6048848916169378},"per_request_limits":null,"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"gryphe/mythomax-l2-13b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4","name":"OpenAI: GPT-4","created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","context_length":8191,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000033,"completion":0.000066,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.270303,"max_completion_cost":0.270336,"max_cost":0.405471},"sats_pricing":{"prompt":0.04140589318785227,"completion":0.08281178637570454,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":339.1556711016979,"max_completion_cost":339.1970769948858,"max_cost":508.7542095991408},"per_request_limits":null,"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/gpt-4","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"embed-5-fast","name":"Cohere: Embed 5 Fast","created":1793739025,"description":"Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). It embeds text, images, and interleaved text and image content...","context_length":128000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":8.800000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.011264000000000001,"max_completion_cost":0.0,"max_cost":0.011264000000000001},"sats_pricing":{"prompt":0.00011041571516760605,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":14.133211541453575,"max_completion_cost":0.0,"max_cost":14.133211541453575},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/embed-5-fast-20261029","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"embed-5-pro","name":"Cohere: Embed 5 Pro","created":1793739016,"description":"Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). It embeds text, images, and interleaved text and image content into...","context_length":128000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.016895999999999998,"max_completion_cost":0.0,"max_cost":0.016895999999999998},"sats_pricing":{"prompt":0.00016562357275140904,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":21.199817312180357,"max_completion_cost":0.0,"max_cost":21.199817312180357},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/embed-5-pro-20261029","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"titan-embed-image-v1","name":"Amazon: Titan Multimodal Embeddings G1","created":1793044729,"description":"Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. Images are sent as base64 (up to...","context_length":128,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.8e-7,"completion":0.0,"request":0.0,"image":0.000066,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00011264,"max_completion_cost":0.0,"max_cost":0.00011264},"sats_pricing":{"prompt":0.0011041571516760605,"completion":0.0,"request":0.001,"image":0.08281178637570454,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.14133211541453575,"max_completion_cost":0.0,"max_cost":0.14133211541453575},"per_request_limits":null,"top_provider":{"context_length":128,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-image-v1-20261026","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"titan-embed-text-v1","name":"Amazon: Titan Embeddings G1 - Text","created":1793044727,"description":"Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. It accepts up to 8,192 tokens per input and returns fixed 1,536-dimension vectors; the `dimensions` parameter is...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00090112,"max_completion_cost":0.0,"max_cost":0.00090112},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.130656923316286,"max_completion_cost":0.0,"max_cost":1.130656923316286},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-text-v1-20261026","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"titan-embed-text-v2","name":"Amazon: Titan Text Embeddings V2","created":1793044722,"description":"Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. It accepts up to 8,192 tokens per input and returns normalized vectors of 1,024 dimensions...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00018022400000000001,"max_completion_cost":0.0,"max_cost":0.00018022400000000001},"sats_pricing":{"prompt":0.000027603928791901512,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2261313846632572,"max_completion_cost":0.0,"max_cost":0.2261313846632572},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-text-v2-20261026","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-code-4","name":"VoyageAI by MongoDB: voyage-code-4","created":1786636912,"description":"voyage-code-4 is a code embedding model from Voyage AI, a MongoDB company. It is designed for coding agents and code retrieval, with Matryoshka embeddings at 2048t voyage-code-4 here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0042239999999999995,"max_completion_cost":0.0,"max_cost":0.0042239999999999995},"sats_pricing":{"prompt":0.00016562357275140904,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.299954328045089,"max_completion_cost":0.0,"max_cost":5.299954328045089},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-code-4-20260812","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-multimodal-3.5","name":"VoyageAI by MongoDB: voyage-multimodal-3.5","created":1785188629,"description":"voyage-multimodal-3.5 is a state-of-the-art multimodal embedding model capable of vectorizing not only text, images, and video individually, but also content that interleaves all three modalities. It delivers excellent performance for...","context_length":32000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0042239999999999995,"max_completion_cost":0.0,"max_cost":0.0042239999999999995},"sats_pricing":{"prompt":0.00016562357275140904,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.299954328045089,"max_completion_cost":0.0,"max_cost":5.299954328045089},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-multimodal-3.5-20260727","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-4-lite","name":"VoyageAI by MongoDB: voyage-4-lite","created":1785188627,"description":"voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings t voyage-4-lite here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0007040000000000001,"max_completion_cost":0.0,"max_cost":0.0007040000000000001},"sats_pricing":{"prompt":0.000027603928791901512,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.8833257213408484,"max_completion_cost":0.0,"max_cost":0.8833257213408484},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-lite-20260727","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-4","name":"VoyageAI by MongoDB: voyage-4","created":1785188626,"description":"voyage-4 is a general-purpose (including multilingual) embedding model optimized for retrieval/search and AI applications. voyage-4 supports embedd about voyage-4 here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0021119999999999997,"max_completion_cost":0.0,"max_cost":0.0021119999999999997},"sats_pricing":{"prompt":0.00008281178637570452,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.6499771640225447,"max_completion_cost":0.0,"max_cost":2.6499771640225447},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-20260727","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-4-large","name":"VoyageAI by MongoDB: voyage-4-large","created":1785188624,"description":"voyage-4-large is a state-of-the-art general-purpose and multilingual embedding optimized for retrieval quality. Enabled by Matryoshka learning and quantization-aware training, voyage-4-large supports embeddings  voyage-4-large here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.32e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0042239999999999995,"max_completion_cost":0.0,"max_cost":0.0042239999999999995},"sats_pricing":{"prompt":0.00016562357275140904,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.299954328045089,"max_completion_cost":0.0,"max_cost":5.299954328045089},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-large-20260727","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-embedding-2","name":"Google: Gemini Embedding 2","created":1779290135,"description":"Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports...","context_length":8192,"architecture":{"modality":"text+image+file+audio+video->embeddings","input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.2e-7,"completion":0.0,"request":0.0,"image":4.95e-7,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00180224,"max_completion_cost":0.0,"max_cost":0.00180224},"sats_pricing":{"prompt":0.00027603928791901513,"completion":0.0,"request":0.001,"image":0.000621088397817784,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.261313846632572,"max_completion_cost":0.0,"max_cost":2.261313846632572},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-2","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"pplx-embed-v1-4b","name":"Perplexity: Embed V1 4B","created":1773625372,"description":"pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval...","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.3e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0010559999999999999,"max_completion_cost":0.0,"max_cost":0.0010559999999999999},"sats_pricing":{"prompt":0.00004140589318785226,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.3249885820112723,"max_completion_cost":0.0,"max_cost":1.3249885820112723},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/pplx-embed-v1-4B","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"pplx-embed-v1-0.6b","name":"Perplexity: Embed V1 0.6B","created":1773624868,"description":"pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency...","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.4000000000000005e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0001408,"max_completion_cost":0.0,"max_cost":0.0001408},"sats_pricing":{"prompt":5.5207857583803025e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.17666514426816968,"max_completion_cost":0.0,"max_cost":0.17666514426816968},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/pplx-embed-v1-0.6B","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gte-base","name":"Thenlper: GTE-Base","created":1763433820,"description":"The gte-base embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, delivering efficient and effective semantic embeddings optimized for textual similarity, semantic search, and clustering applications.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.900982197975378e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035333028853633936,"max_completion_cost":0.0,"max_cost":0.0035333028853633936},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thenlper/gte-base-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gte-large","name":"Thenlper: GTE-Large","created":1763433655,"description":"The gte-large embedding model converts English sentences, paragraphs and moderate-length documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for information retrieval, semantic textual similarity, reranking and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.6320000000000005e-6,"max_completion_cost":0.0,"max_cost":5.6320000000000005e-6},"sats_pricing":{"prompt":0.000013801964395950756,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007066605770726787,"max_completion_cost":0.0,"max_cost":0.007066605770726787},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thenlper/gte-large-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e5-large-v2","name":"Intfloat: E5-Large-v2","created":1763433432,"description":"The e5-large-v2 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-accuracy semantic embeddings optimized for retrieval, semantic search, reranking, and similarity-scoring tasks.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.6320000000000005e-6,"max_completion_cost":0.0,"max_cost":5.6320000000000005e-6},"sats_pricing":{"prompt":0.000013801964395950756,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007066605770726787,"max_completion_cost":0.0,"max_cost":0.007066605770726787},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/e5-large-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e5-base-v2","name":"Intfloat: E5-Base-v2","created":1763433192,"description":"The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, similarity scoring,...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.900982197975378e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035333028853633936,"max_completion_cost":0.0,"max_cost":0.0035333028853633936},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/e5-base-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"multilingual-e5-large","name":"Intfloat: Multilingual-E5-Large","created":1763433047,"description":"The multilingual-e5-large embedding model encodes sentences, paragraphs, and documents across over 90 languages into a 1024-dimensional dense vector space, delivering robust semantic embeddings optimized for multilingual retrieval, cross-language similarity, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.6320000000000005e-6,"max_completion_cost":0.0,"max_cost":5.6320000000000005e-6},"sats_pricing":{"prompt":0.000013801964395950756,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007066605770726787,"max_completion_cost":0.0,"max_cost":0.007066605770726787},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/multilingual-e5-large-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"paraphrase-minilm-l6-v2","name":"Sentence Transformers: paraphrase-MiniLM-L6-v2","created":1763432454,"description":"The paraphrase-MiniLM-L6-v2 embedding model converts sentences and short paragraphs into a 384-dimensional dense vector space, producing high-quality semantic embeddings optimized for paraphrase detection, semantic similarity scoring, clustering, and lightweight retrieval...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.900982197975378e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035333028853633936,"max_completion_cost":0.0,"max_cost":0.0035333028853633936},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/paraphrase-minilm-l6-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"all-minilm-l12-v2","name":"Sentence Transformers: all-MiniLM-L12-v2","created":1763432155,"description":"The all-MiniLM-L12-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, clustering, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.900982197975378e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035333028853633936,"max_completion_cost":0.0,"max_cost":0.0035333028853633936},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-minilm-l12-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"multi-qa-mpnet-base-dot-v1","name":"Sentence Transformers: multi-qa-mpnet-base-dot-v1","created":1763431339,"description":"The multi-qa-mpnet-base-dot-v1 embedding model transforms sentences and short paragraphs into a 768-dimensional dense vector space, generating high-quality semantic embeddings optimized for question-and-answer retrieval, semantic search, and similarity-scoring across diverse content.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.900982197975378e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035333028853633936,"max_completion_cost":0.0,"max_cost":0.0035333028853633936},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"bge-large-en-v1.5","name":"BAAI: bge-large-en-v1.5","created":1763431087,"description":"The bge-large-en-v1.5 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-fidelity semantic embeddings optimized for semantic search, document retrieval, and downstream NLP tasks...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.6320000000000005e-6,"max_completion_cost":0.0,"max_cost":5.6320000000000005e-6},"sats_pricing":{"prompt":0.000013801964395950756,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007066605770726787,"max_completion_cost":0.0,"max_cost":0.007066605770726787},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-large-en-v1.5-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"bge-m3","name":"BAAI: bge-m3","created":1763424372,"description":"The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.","context_length":8194,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.000090134,"max_completion_cost":0.0,"max_cost":0.000090134},"sats_pricing":{"prompt":0.000013801964395950756,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.11309329626042049,"max_completion_cost":0.0,"max_cost":0.11309329626042049},"per_request_limits":null,"top_provider":{"context_length":8194,"max_completion_tokens":8194,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-m3-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"all-mpnet-base-v2","name":"Sentence Transformers: all-mpnet-base-v2","created":1763421830,"description":"The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.900982197975378e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035333028853633936,"max_completion_cost":0.0,"max_cost":0.0035333028853633936},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-mpnet-base-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"all-minilm-l6-v2","name":"Sentence Transformers: all-MiniLM-L6-v2","created":1763421176,"description":"The all-MiniLM-L6-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, enabling high-quality semantic representations that are ideal for downstream tasks such as information retrieval, clustering,...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.5000000000000004e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.8160000000000002e-6,"max_completion_cost":0.0,"max_cost":2.8160000000000002e-6},"sats_pricing":{"prompt":6.900982197975378e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0035333028853633936,"max_completion_cost":0.0,"max_cost":0.0035333028853633936},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-minilm-l6-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-embed-2312","name":"Mistral: Mistral Embed 2312","created":1761944622,"description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00090112,"max_completion_cost":0.0,"max_cost":0.00090112},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.130656923316286,"max_completion_cost":0.0,"max_cost":1.130656923316286},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-embed-2312","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-embedding-001","name":"Google: Gemini Embedding 001","created":1761943410,"description":"gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark...","context_length":20000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0033,"max_completion_cost":0.0,"max_cost":0.0033},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.140589318785226,"max_completion_cost":0.0,"max_cost":4.140589318785226},"per_request_limits":null,"top_provider":{"context_length":20000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-001","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-ada-002","name":"OpenAI: Text Embedding Ada 002","created":1761865798,"description":"text-embedding-ada-002 is OpenAI's legacy text embedding model.","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00090112,"max_completion_cost":0.0,"max_cost":0.00090112},"sats_pricing":{"prompt":0.00013801964395950757,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.130656923316286,"max_completion_cost":0.0,"max_cost":1.130656923316286},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/text-embedding-ada-002","alias_ids":["text-embedding-ada-002-v2"],"forwarded_model_id":null,"image_pricing":null},{"id":"codestral-embed-2505","name":"Mistral: Codestral Embed 2505","created":1761864460,"description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.65e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00135168,"max_completion_cost":0.0,"max_cost":0.00135168},"sats_pricing":{"prompt":0.00020702946593926133,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.6959853849744289,"max_completion_cost":0.0,"max_cost":1.6959853849744289},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/codestral-embed-2505","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-3-large","name":"OpenAI: Text Embedding 3 Large","created":1761862866,"description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.4300000000000002e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0011714560000000002,"max_completion_cost":0.0,"max_cost":0.0011714560000000002},"sats_pricing":{"prompt":0.00017942553714735983,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.4698540003111717,"max_completion_cost":0.0,"max_cost":1.4698540003111717},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/text-embedding-3-large","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-3-small","name":"OpenAI: Text Embedding 3 Small","created":1761857455,"description":"text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00018022400000000001,"max_completion_cost":0.0,"max_cost":0.00018022400000000001},"sats_pricing":{"prompt":0.000027603928791901512,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2261313846632572,"max_completion_cost":0.0,"max_cost":0.2261313846632572},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"openai/text-embedding-3-small","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-embedding-8b","name":"Qwen: Qwen3 Embedding 8B","created":1761680622,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...","context_length":40960,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.1000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00045056,"max_completion_cost":0.0,"max_cost":0.00009856},"sats_pricing":{"prompt":0.000013801964395950756,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.565328461658143,"max_completion_cost":0.0,"max_cost":0.12366560098771877},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":32000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-embedding-8b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-embedding-4b","name":"Qwen: Qwen3 Embedding 4B","created":1761662922,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...","context_length":32768,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0007208960000000001,"max_completion_cost":0.0,"max_cost":0.0007208960000000001},"sats_pricing":{"prompt":0.000027603928791901512,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.9045255386530288,"max_completion_cost":0.0,"max_cost":0.9045255386530288},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-embedding-4b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"riverflow-v2.6-pro","name":"Sourceful: Riverflow V2.6 Pro","created":1793289528,"description":"Riverflow 2.6 Pro is the flagship model of Sourceful's Riverflow 2.6 lineup, a unified text-to-image and image-to-image family that treats generation as a production workflow: an integrated reasoning model plans...","context_length":32768,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.18700000000000003,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.7480000000000001,"max_cost":0.7480000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":234.63339473116287,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":938.5335789246515,"max_cost":938.5335789246515},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sourceful/riverflow-v2.6-pro-20261029","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":{"max_usd":0.17,"tiers":[{"resolution":null,"quality":null,"usd":0.17}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"sourceful":{"max_usd":0.17,"tiers":[{"resolution":null,"quality":null,"usd":0.17}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"sourceful","parameters":{"resolution":{"type":"enum","values":["1K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","3:2","2:3","5:4","4:5","16:9","9:16","21:9","auto"]},"output_format":{"type":"enum","values":["png","jpeg","webp"]},"background":{"type":"enum","values":["auto","transparent","opaque"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":10},"size":{"type":"boolean"}},"unreported_cost_usd":0.13}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2.1-turbo","name":"Qwen: Qwen Image 2.1 Turbo","created":1792194104,"description":"Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.02024,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.08096,"max_cost":0.08096},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":25.39561448854939,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":101.58245795419757,"max_cost":101.58245795419757},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-image-2.1-turbo-20261016","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.0184,"tiers":[{"resolution":null,"quality":null,"usd":0.0184}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"alibaba":{"max_usd":0.0184,"tiers":[{"resolution":null,"quality":null,"usd":0.0184}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"alibaba","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","1:4","2:1","2:3","3:2","3:4","4:1","4:3","4:5","5:4","9:16","16:9"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":4},"seed":{"type":"boolean"}},"unreported_cost_usd":0.0184}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2.1-pro","name":"Qwen: Qwen Image 2.1 Pro","created":1792194075,"description":"Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.050600000000000006,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.20240000000000002,"max_cost":0.20240000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":63.48903622137348,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":253.95614488549393,"max_cost":253.95614488549393},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-image-2.1-pro-20261016","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.046,"tiers":[{"resolution":null,"quality":null,"usd":0.046}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"alibaba":{"max_usd":0.046,"tiers":[{"resolution":null,"quality":null,"usd":0.046}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"alibaba","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","1:4","2:1","2:3","3:2","3:4","4:1","4:3","4:5","5:4","9:16","16:9"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":4},"seed":{"type":"boolean"}},"unreported_cost_usd":0.046}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux-3-image-klein","name":"Black Forest Labs: FLUX 3 Image Klein","created":1792083863,"description":"FLUX 3 Image Klein is an open-weights image generation and editing model from Black Forest Labs. It is suited for text-to-image, multi-reference editing that keeps characters and subjects consistent across...","context_length":46864,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0396,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.1584,"max_cost":0.1584},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":49.68707182542272,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":198.74828730169088,"max_cost":198.74828730169088},"per_request_limits":null,"top_provider":{"context_length":46864,"max_completion_tokens":42177,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"black-forest-labs/flux-3-image-klein-20261015","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.036,"tiers":[{"resolution":null,"quality":null,"usd":0.036}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"black-forest-labs":{"max_usd":0.036,"tiers":[{"resolution":null,"quality":null,"usd":0.036}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"black-forest-labs","parameters":{"resolution":{"type":"enum","values":["768","1K","1.5K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["21:9","2:1","16:9","3:2","7:5","4:3","5:4","1:1","4:5","3:4","5:7","2:3","9:16","1:2","9:21","auto"]},"output_format":{"type":"enum","values":["jpeg","png"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":10},"seed":{"type":"boolean"}},"unreported_cost_usd":0.008}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-5-0-flash","name":"ByteDance Seed: Seedream 5.0 Flash","created":1790889880,"description":"Seedream 5.0 Flash is an image generation and editing model from ByteDance Seed. It is the fast, cost-efficient tier of the Seedream 5.0 family, suited for high-volume production and interactive...","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0198,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.0792,"max_cost":0.0792},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":24.84353591271136,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":99.37414365084544,"max_cost":99.37414365084544},"per_request_limits":null,"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seedream-5-0-flash-20261001","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.018,"tiers":[{"resolution":null,"quality":null,"usd":0.018}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"seed":{"max_usd":0.018,"tiers":[{"resolution":null,"quality":null,"usd":0.018}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"seed","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","2:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","9:19.5","19.5:9","9:20","20:9","9:21","21:9","auto"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":14},"seed":{"type":"boolean"}},"unreported_cost_usd":0.018}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-flash","name":"Recraft: Recraft V4.1 Flash","created":1790177946,"description":"Recraft V4.1 Flash is a text-to-image model from Recraft, the speed and cost tier of the V4.1 family. It generates ~1K raster images in about 1.5 seconds end to end,...","context_length":65536,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.007700000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.030800000000000004,"max_cost":0.030800000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":9.66137507716553,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":38.64550030866212,"max_cost":38.64550030866212},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-flash-20260923","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.007,"tiers":[{"resolution":null,"quality":null,"usd":0.007}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.007,"tiers":[{"resolution":null,"quality":null,"usd":0.007}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6}},"unreported_cost_usd":0.007}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-5-0-lite","name":"ByteDance Seed: Seedream 5.0 Lite","created":1786650094,"description":"Seedream 5.0 Lite is an image generation model from ByteDance Seed. It is suited for professional visual creation that benefits from web-connected retrieval, complex-prompt comprehension, visual references, and broad knowledge...","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.038500000000000006,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.15400000000000003,"max_cost":0.15400000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":48.30687538582765,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":193.2275015433106,"max_cost":193.2275015433106},"per_request_limits":null,"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seedream-5-0-lite-20260812","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"seed":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"seed","parameters":{"resolution":{"type":"enum","values":["2K","4K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","2:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","9:19.5","19.5:9","9:20","20:9","9:21","21:9","auto"]},"n":{"type":"range","min":1,"max":4},"input_references":{"type":"range","min":0,"max":14},"seed":{"type":"boolean"}},"unreported_cost_usd":0.035}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-5-0-pro","name":"ByteDance Seed: Seedream 5.0 Pro","created":1786578139,"description":"Seedream 5.0 Pro is an image generation and editing model from ByteDance Seed. It is suited for commercial visual-production workflows that require precise editing control, lifelike scenes, and natural rendering.","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0033000000000000004,"image_output":0.099,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0033000000000000004,"max_completion_cost":0.396,"max_cost":0.39930000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":4.140589318785227,"image_output":124.2176795635568,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.140589318785227,"max_completion_cost":496.8707182542272,"max_cost":501.01130757301246},"per_request_limits":null,"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seedream-5-0-pro-20260812","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.09,"tiers":[{"resolution":null,"quality":null,"usd":0.09}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"seed":{"max_usd":0.09,"tiers":[{"resolution":null,"quality":null,"usd":0.09}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"seed","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","2:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","9:19.5","19.5:9","9:20","20:9","9:21","21:9","auto"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":14},"seed":{"type":"boolean"}},"unreported_cost_usd":0.045}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"grok-imagine-image-2.0","name":"xAI: Grok Imagine Image 2.0","created":1786486044,"description":"Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.011000000000000001,"image_output":0.08800000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.011000000000000001,"max_completion_cost":0.35200000000000004,"max_cost":0.36300000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":13.801964395950757,"image_output":110.41571516760605,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":13.801964395950757,"max_completion_cost":441.6628606704242,"max_cost":455.46482506637494},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-imagine-image-2.0-20260811","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.01,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"xai":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.01,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"xai","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","3:4","4:3","9:16","16:9","2:3","3:2","9:19.5","19.5:9","9:20","20:9","1:2","2:1","auto"]},"quality":{"type":"enum","values":["low","medium"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":3}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-2-large","name":"Krea: Krea 2 Large","created":1784574931,"description":"Krea 2 Large is Krea's high-capability image generation model, more than twice the size of Krea 2 Medium. Its lighter post-training gives images a rawer, more textured, and flexible character,...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.07700000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.30800000000000005,"max_cost":0.30800000000000005},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":96.6137507716553,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":386.4550030866212,"max_cost":386.4550030866212},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"krea/krea-2-large-20260720","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.07,"tiers":[{"resolution":null,"quality":null,"usd":0.07}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"krea":{"max_usd":0.07,"tiers":[{"resolution":null,"quality":null,"usd":0.07}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"krea","parameters":{"resolution":{"type":"enum","values":["1K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:2","16:9","4:5","2:3","9:16"]},"input_references":{"type":"range","min":0,"max":1},"seed":{"type":"boolean"}},"unreported_cost_usd":0.06}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-2-medium","name":"Krea: Krea 2 Medium","created":1784574928,"description":"Krea 2 Medium is Krea's balanced, cost-efficient image generation model and a practical starting point for a broad range of use cases. Its extensive post-training supports stable, consistent generations, with...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.17600000000000002,"max_cost":0.17600000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":220.8314303352121,"max_cost":220.8314303352121},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"krea/krea-2-medium-20260720","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"krea":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"krea","parameters":{"resolution":{"type":"enum","values":["1K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:2","16:9","4:5","2:3","9:16"]},"input_references":{"type":"range","min":0,"max":1},"seed":{"type":"boolean"}},"unreported_cost_usd":0.03}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-2-medium-turbo","name":"Krea: Krea 2 Medium Turbo","created":1784574923,"description":"Krea 2 Medium Turbo is a distilled, speed-focused variant of Krea 2 Medium from Krea. It is designed for rapid iteration and graphic design exploration where fast generation is the...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.022000000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.08800000000000001,"max_cost":0.08800000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":27.603928791901513,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":110.41571516760605,"max_cost":110.41571516760605},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"krea/krea-2-medium-turbo-20260720","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.02,"tiers":[{"resolution":null,"quality":null,"usd":0.02}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"krea":{"max_usd":0.02,"tiers":[{"resolution":null,"quality":null,"usd":0.02}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"krea","parameters":{"resolution":{"type":"enum","values":["1K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:2","16:9","4:5","2:3","9:16"]},"input_references":{"type":"range","min":0,"max":1},"seed":{"type":"boolean"}},"unreported_cost_usd":0.015}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"riverflow-v2.5-pro","name":"Sourceful: Riverflow V2.5 Pro","created":1780584991,"description":"Riverflow V2.5 Pro is the most powerful variant of Sourceful's Riverflow 2.5 lineup, best for top-tier control and quality-sensitive outputs. The Riverflow 2.5 series is a unified text-to-image and image-to-image...","context_length":32768,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.18700000000000003,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.7480000000000001,"max_cost":0.7480000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":234.63339473116287,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":938.5335789246515,"max_cost":938.5335789246515},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sourceful/riverflow-v2.5-pro-20260605","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":{"max_usd":0.17,"tiers":[{"resolution":null,"quality":null,"usd":0.17}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"sourceful":{"max_usd":0.17,"tiers":[{"resolution":null,"quality":null,"usd":0.17}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"sourceful","parameters":{"resolution":{"type":"enum","values":["1K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","3:2","2:3","16:9","9:16","21:9","auto"]},"output_format":{"type":"enum","values":["png","jpeg","webp"]},"background":{"type":"enum","values":["auto","transparent","opaque"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":10}},"unreported_cost_usd":0.13}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"riverflow-v2.5-fast","name":"Sourceful: Riverflow V2.5 Fast","created":1780584983,"description":"Riverflow V2.5 Fast is the speed-optimized variant of Sourceful's Riverflow 2.5 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.5 series is a unified text-to-image and image-to-image family...","context_length":32768,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.023100000000000002,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.09240000000000001,"max_cost":0.09240000000000001},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":28.984125231496588,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":115.93650092598635,"max_cost":115.93650092598635},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sourceful/riverflow-v2.5-fast-20260605","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":{"max_usd":0.021,"tiers":[{"resolution":null,"quality":null,"usd":0.021}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"sourceful":{"max_usd":0.021,"tiers":[{"resolution":null,"quality":null,"usd":0.021}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"sourceful","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","3:2","2:3","16:9","9:16","21:9","auto"]},"output_format":{"type":"enum","values":["jpeg"]},"background":{"type":"enum","values":["auto","transparent","opaque"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":4}},"unreported_cost_usd":0.019}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-pro-vector","name":"Recraft: Recraft V4.1 Pro Vector","created":1778707395,"description":"Recraft V4.1 Pro Vector is the vector (SVG) variant of Recraft V4.1 Pro, tuned for high aesthetics. It supports text and image inputs and produces higher-resolution SVG image output across...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.33,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.32,"max_cost":1.32},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":414.0589318785227,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1656.2357275140907,"max_cost":1656.2357275140907},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-pro-vector-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.3,"tiers":[{"resolution":null,"quality":null,"usd":0.3}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.3,"tiers":[{"resolution":null,"quality":null,"usd":0.3}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"output_format":{"type":"enum","values":["svg"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.3}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-vector","name":"Recraft: Recraft V4.1 Vector","created":1778707392,"description":"Recraft V4.1 Vector is the vector (SVG) variant of Recraft V4.1, tuned for high aesthetics. It supports text and image inputs and produces SVG image output across multiple aspect ratios,...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.08800000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.35200000000000004,"max_cost":0.35200000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":110.41571516760605,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":441.6628606704242,"max_cost":441.6628606704242},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-vector-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"output_format":{"type":"enum","values":["svg"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.08}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-utility-pro","name":"Recraft: Recraft V4.1 Utility Pro","created":1778707389,"description":"Recraft V4.1 Utility Pro is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios — double...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.231,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.924,"max_cost":0.924},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":289.84125231496586,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1159.3650092598634,"max_cost":1159.3650092598634},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-utility-pro-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.21,"tiers":[{"resolution":null,"quality":null,"usd":0.21}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.21,"tiers":[{"resolution":null,"quality":null,"usd":0.21}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.21}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-utility","name":"Recraft: Recraft V4.1 Utility","created":1778707387,"description":"Recraft V4.1 Utility is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with typical generation...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.038500000000000006,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.15400000000000003,"max_cost":0.15400000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":48.30687538582765,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":193.2275015433106,"max_cost":193.2275015433106},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-utility-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.035}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-pro","name":"Recraft: Recraft V4.1 Pro","created":1778707384,"description":"Recraft V4.1 Pro is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.231,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.924,"max_cost":0.924},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":289.84125231496586,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1159.3650092598634,"max_cost":1159.3650092598634},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-pro-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.21,"tiers":[{"resolution":null,"quality":null,"usd":0.21}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.21,"tiers":[{"resolution":null,"quality":null,"usd":0.21}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.21}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1","name":"Recraft: Recraft V4.1","created":1778707381,"description":"Recraft V4.1 is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.038500000000000006,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.15400000000000003,"max_cost":0.15400000000000003},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":48.30687538582765,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":193.2275015433106,"max_cost":193.2275015433106},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.035}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4-pro-vector","name":"Recraft: Recraft V4 Pro Vector","created":1778707334,"description":"Recraft V4 Pro Vector is the vector (SVG) variant of Recraft V4 Pro. It supports text and image inputs and produces vector image output across multiple aspect ratios at the...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.33,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.32,"max_cost":1.32},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":414.0589318785227,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1656.2357275140907,"max_cost":1656.2357275140907},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4-pro-vector-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.3,"tiers":[{"resolution":null,"quality":null,"usd":0.3}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.3,"tiers":[{"resolution":null,"quality":null,"usd":0.3}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"output_format":{"type":"enum","values":["svg"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.3}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4-vector","name":"Recraft: Recraft V4 Vector","created":1778707333,"description":"Recraft V4 Vector is the vector (SVG) variant of Recraft V4. It supports text and image inputs and produces vector image output across multiple aspect ratios. Compared to the raster...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.08800000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.35200000000000004,"max_cost":0.35200000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":110.41571516760605,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":441.6628606704242,"max_cost":441.6628606704242},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4-vector-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"output_format":{"type":"enum","values":["svg"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.08}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v3","name":"Recraft: Recraft V3","created":1778185433,"description":"Recraft V3 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. Supports the following `image_config` parameters:...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.17600000000000002,"max_cost":0.17600000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":220.8314303352121,"max_cost":220.8314303352121},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v3-20260413","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-4.5","name":"ByteDance Seed: Seedream 4.5","created":1766519506,"description":"Seedream 4.5 is the latest in-house image generation model developed by ByteDance. Compared with Seedream 4.0, it delivers comprehensive improvements, especially in editing consistency, including better preservation of subject details,...","context_length":4096,"architecture":{"modality":"text+image->image","input_modalities":["image","text"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.044000000000000004,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.17600000000000002,"max_cost":0.17600000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":55.207857583803026,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":220.8314303352121,"max_cost":220.8314303352121},"per_request_limits":null,"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seedream-4.5-20251203","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"seed":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"seed","parameters":{"resolution":{"type":"enum","values":["1K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","2:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","9:19.5","19.5:9","9:20","20:9","9:21","21:9","auto"]},"n":{"type":"range","min":1,"max":10},"input_references":{"type":"range","min":0,"max":14},"seed":{"type":"boolean"}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}}]}