NewOpenAI- and Anthropic-compatible — no migrationRead the announcement
OpenAI-compatible

Chat completions

Creates a completion for a chat conversation. Compatible with OpenAI's chat.completions.create endpoint.

POST /openai/v1/chat/completions

The full OpenAI surface — same request body, same response shape, same streaming behavior.

Request body parameters
model       string  Required   The model ID to use. See /docs/models-api.messages    array   Required   [{ role: "system"|"user"|"assistant", content: ... }]max_tokens  int     Optional   Max tokens to generate. Default: model's max context.temperature float   Optional   Sampling temperature 0–2. Default: 1.top_p       float   Optional   Nucleus sampling probability. Default: 1.stream      bool    Optional   Whether to stream partial tokens via SSE. Default: false.response_format object Optional  {"type":"json_object"} to force JSON output.tools       array   Optional   List of tools the model may call. See function calling.
Python
response = client.chat.completions.create(    model="deepseek-ai/DeepSeek-R1-0528",    messages=[        {"role": "system", "content": "You are a helpful assistant."},        {"role": "user", "content": "What is 2+2?"},    ],    temperature=0.7,    max_tokens=256,) print(response.choices[0].message.content)