What does 413 request_too_large mean?

The request is over 3 MB or has more than 800 messages.

Code: request_too_large · HTTP status: 413

The limit is on the request itself, separate from the model's 1M-token context window.

Common causes#

• a long chat history sent in full on every turn
• a huge pasted file or log
• more than 800 messages after many tool calls

How to fix it#

1. Trim or summarise old turns.
2. Send only the parts of a file that matter.
3. Check you're not accidentally duplicating history each turn.

Should my code retry?#

Not retryable until the request is smaller.

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

{"error": {"message": "...", "type": "...", "code": "request_too_large", "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.