{"object":"list","data":[{"id":"gpt-oss-120b","object":"model","created":1754438400,"owned_by":"OpenAI","name":"OpenAI GPT OSS","description":"This model excels at efficient reasoning across science, math, and coding applications. It's ideal for real-time coding assistance, processing large documents for Q&A and summarization, agentic research workflows, and regulated on-premises workloads.","hugging_face_id":"openai/gpt-oss-120b","pricing":{"prompt":"0.00000035","completion":"0.00000075"},"capabilities":{"streaming":true,"function_calling":true,"structured_outputs":true,"vision":false,"json_mode":true,"tools":true,"tool_choice":true,"parallel_tool_calls":false,"response_format":true,"reasoning":true},"supported_parameters":{"temperature":true,"top_p":true,"seed":true,"stop":true,"max_completion_tokens":true,"logprobs":false,"top_logprobs":false,"frequency_penalty":true,"presence_penalty":true,"logit_bias":true,"repetition_penalty":false},"architecture":{"modality":"text","tokenizer":"GPT","instruct_type":"harmony"},"limits":{"max_context_length":131072,"max_completion_tokens":40960,"requests_per_minute":null,"tokens_per_minute":null},"datacenter_locations":[],"deprecated":false,"preview":false,"quantization":"FP16/8 (weights only)"},{"id":"qwen-3.8-27b","object":"model","created":0,"owned_by":"Cerebras","name":"Qwen 3.8 27B","description":"This model excels at vision-language understanding, coding, research, and long-horizon agentic tasks.","hugging_face_id":"Qwen/Qwen3.8-27B","pricing":{"prompt":"0.00000099","completion":"0.00000149"},"capabilities":{"streaming":true,"function_calling":true,"structured_outputs":true,"vision":true,"json_mode":true,"tools":true,"tool_choice":true,"parallel_tool_calls":true,"response_format":true,"reasoning":true},"supported_parameters":{"temperature":true,"top_p":true,"seed":true,"stop":true,"max_completion_tokens":true,"logprobs":true,"top_logprobs":true,"frequency_penalty":true,"presence_penalty":true,"logit_bias":true,"repetition_penalty":false},"architecture":{"modality":"text+vision","tokenizer":"Qwen","instruct_type":"qwen"},"limits":{"max_context_length":65536,"max_completion_tokens":32768,"requests_per_minute":null,"tokens_per_minute":null},"datacenter_locations":[],"deprecated":false,"preview":false,"quantization":"FP16/FP8"}]}