What does 400 invalid_request mean on the Model API?

The request body isn't valid for POST /v1/chat/completions. Check the required fields and the field types.

Code: invalid_request · HTTP status: 400

The body is missing something required or a field has the wrong shape. Fix the request; sending it again unchanged gives the same error.

Common causes#

• model or messages is missing
• messages isn't an array of objects with a role and content
• a tool message has no tool_call_id
• a number is out of range, such as temperature above 2 or top_p of 0
• more than 4 stop sequences

How to fix it#

1. Read error.message and error.param: they name the field that failed.
2. Compare your body with the Create a chat completion reference.
3. Send a minimal body (model plus one user message). If that works, add your other fields back one at a time.

Should my code retry?#

Don't retry automatically: a 400 is a problem in the request, not on our side.

The error body uses the OpenAI shape, so OpenAI SDKs raise it as an exception you can catch:

{"error": {"message": "...", "type": "...", "code": "invalid_request", "param": null}}

Every response also carries an X-Request-Id. Keep it in your logs; it's the quickest way for support to find a request.

See the full list in the Model API reference.

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.