{"data":[{"schema_version":"2.4","id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","created":1733356800,"quantization":"fp8","tokenizer":"Llama3","description":"Llama 3.3 70B Instruct served on NVIDIA B200 / H100 with continuous batching & vLLM.","input_modalities":[{"type":"text","supported_inputs":{"max_context_length":{"value":131072,"unit":"token"}},"pricing":[{"type":"prompt","unit":"token","cost_usd":"0.0000001"}],"capacity":[{"type":"prompt","unit":"token","per":"minute","value":3000000}]}],"output_modalities":[{"type":"text","max_length":{"value":8192,"unit":"token"},"streaming":true,"supported_parameters":{"temperature":{"type":"range","min":0,"max":2},"top_p":{"type":"range","min":0,"max":1},"max_tokens":{"type":"integer","min":1,"max":8192,"unit":"token"},"stop":{"type":"array","max_items":4},"tools":{"type":"boolean"},"structured_outputs":{"type":"boolean"}},"pricing":[{"type":"completion","unit":"token","cost_usd":"0.00000032"}],"capacity":[{"type":"completion","unit":"token","per":"minute","value":300000}]}],"capacity":[{"type":"request","unit":"request","per":"minute","value":300}],"is_ready":true,"is_free":false,"openrouter":{"slug":"meta-llama/llama-3.3-70b-instruct"},"datacenters":[{"country_code":"US","region":"us"}],"deployment_region":"US"}]}