Back to catalog

Openrouter · Ai Models

OpenRouter / Chat completion

Runs a chat completion on one of 15 current models (OpenAI GPT-6 Luna and GPT-5.4, Gemini 3.8 Flash, DeepSeek v4, Qwen 3.8, GLM 5.3, Kimi K2.6, Mistral Small, Grok). messages is the usual [{role, content}] list; max_tokens (1-16000) is required and caps the answer (reasoning tokens count toward it). Returns choices[0].message.content and usage with the exact cost. OpenAI-compatible request and response.

Live data

You are looking at the live public catalog.

unverifiedRequest shape unavailableUnverified
Published API evidence
Public metadata only. Response bodies, credentials, and internal review notes are never displayed.

No verification date is claimed. No response capture is claimed.

Request parameters

  • max_tokens body · required
  • messages body · required
  • model body · required
  • response_format body · optional

    e.g. {"type":"json_object"} or a json_schema

  • seed body · optional
  • stop body · optional
  • temperature body · optional
  • top_p body · optional
Provider docs How to run it

Sign in to run this operation, inspect live eligibility, and see governed execution and audit evidence. Sign in.