{"chat_completions":{"path":"/v1/chat/completions","method":"POST","kind":"inference","tier":"deepseek","description":"OpenAI-compatible chat completions over DeepSeek V4 Flash, Qwen3.8-27B or MiniMax M2.7. The model is required. Price is a flat amount in one of two bands (prompt under or over ~4,000 estimated tokens), set by the model; there is no peak-hour surcharge. Additional OpenAI parameters (temperature, max_tokens, top_p, frequency_penalty, presence_penalty, stop, etc.) are forwarded. The optional metered (`upto`) accept authorizes the prompt plus your `max_tokens` as a ceiling and settles the measured input and output tokens. Streaming is not supported on the paid route.","parameters":{"model":{"type":"string","description":"Required. The Hyperfusion model id to serve","enum":["deepseek-ai/DeepSeek-V4-Flash-0731","Qwen/Qwen3.8-27B","MiniMaxAI/MiniMax-M2.7"]},"messages":{"type":"array","description":"Chat messages in OpenAI format","items":{"type":"object","properties":{"role":{"type":"string","enum":["system","user","assistant","tool"]},"content":{"type":"string","description":"Message content"}},"required":["role","content"]}},"stream":{"type":"boolean","description":"Must be false or omitted. The paid route buffers the completion so it can settle against the usage it consumed."}},"required":["model","messages"],"output_example":{"choices":[{"message":{"role":"assistant","content":"The capital of France is Paris."}}]},"latency_class":"medium"}}