{"source":"https://models.dev/api.json","loaded_at":"2026-08-10T18:48:05.216Z","pricing":"provider-declared (per 1M tokens, USD); jishie-measured evals are a later step","total":9,"returned":9,"models":[{"key":"inference/qwen/qwen3-embedding-4b","model":"qwen/qwen3-embedding-4b","name":"Qwen 3 Embedding 4B","provider":"inference","provider_name":"Inference","family":"qwen","input_per_mtok":0.01,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32000,"max_output":2048,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"inference/meta/llama-3.2-1b-instruct","model":"meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","provider":"inference","provider_name":"Inference","family":"llama","input_per_mtok":0.01,"output_per_mtok":0.01,"cache_read_per_mtok":null,"context":16000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"inference/meta/llama-3.2-3b-instruct","model":"meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","provider":"inference","provider_name":"Inference","family":"llama","input_per_mtok":0.02,"output_per_mtok":0.02,"cache_read_per_mtok":null,"context":16000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"inference/meta/llama-3.1-8b-instruct","model":"meta/llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","provider":"inference","provider_name":"Inference","family":"llama","input_per_mtok":0.025,"output_per_mtok":0.025,"cache_read_per_mtok":null,"context":16000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"inference/mistral/mistral-nemo-12b-instruct","model":"mistral/mistral-nemo-12b-instruct","name":"Mistral Nemo 12B Instruct","provider":"inference","provider_name":"Inference","family":"mistral-nemo","input_per_mtok":0.038,"output_per_mtok":0.1,"cache_read_per_mtok":null,"context":16000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"inference/meta/llama-3.2-11b-vision-instruct","model":"meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","provider":"inference","provider_name":"Inference","family":"llama","input_per_mtok":0.055,"output_per_mtok":0.055,"cache_read_per_mtok":null,"context":16000,"max_output":4096,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"inference/google/gemma-3","model":"google/gemma-3","name":"Google Gemma 3","provider":"inference","provider_name":"Inference","family":"gemma","input_per_mtok":0.15,"output_per_mtok":0.3,"cache_read_per_mtok":null,"context":125000,"max_output":4096,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"inference/qwen/qwen-2.5-7b-vision-instruct","model":"qwen/qwen-2.5-7b-vision-instruct","name":"Qwen 2.5 7B Vision Instruct","provider":"inference","provider_name":"Inference","family":"qwen","input_per_mtok":0.2,"output_per_mtok":0.2,"cache_read_per_mtok":null,"context":125000,"max_output":4096,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"inference/osmosis/osmosis-structure-0.6b","model":"osmosis/osmosis-structure-0.6b","name":"Osmosis Structure 0.6B","provider":"inference","provider_name":"Inference","family":"osmosis","input_per_mtok":0.1,"output_per_mtok":0.5,"cache_read_per_mtok":null,"context":4000,"max_output":2048,"modalities":["text"],"tool_call":true,"reasoning":false}]}