What does a Model API error look like?

Model API errors use the OpenAI error shape, with a stable code you can branch on and a message written for people.

{
  "error": {
    "message": "The model \"foo\" does not exist. See GET /v1/models.",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": null
  }
}

The fields#

• code: stable and machine-readable. Branch on this, never on the message text.
• message: a human explanation. It can change wording over time.
• type: the OpenAI-style category, such as authentication_error, invalid_request_error or permission_error.
• param: the field that caused the error, when there is one (for example model).

Some errors add fields: account_suspended carries resets_at, appeal_url and policy_url; model_retired carries replacement and retired_at.

Headers#

• X-Request-Id on every response, success or error.
• Retry-After on 429 and on many 5xx responses, in seconds.

Status codes at a glance#

Source: 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.