Skip to main content

​
Wrong Base URL?

Do not mix the two credential surfaces.

​
401 / 403 / 402 / 429

​
Account quota errors on OpenAI text endpoints

POST /v1/completions, /v1/chat/completions, /v1/responses, and /v1/responses/compact return 402 with error.type and error.code set to insufficient_quota when the local account balance or subscription quota cannot cover pre-consume. This includes zero balance and a positive balance below the required amount.
A streaming request receives the same JSON error before an SSE stream starts. Treat this as a terminal quota failure: check the account balance or subscription allowance before trying again. Do not refresh credentials, switch channels, or retry with backoff solely because of this response. The message includes a request ID; detailed quota amounts remain in server diagnostics. This normalization is limited to local account-quota failures on these endpoints. Token validity/quota errors, upstream provider errors, and other API protocols keep their existing contracts. A genuine 401 or permission 403 still requires an authentication/access check; an ordinary 429 remains a rate-limit response.

​
Unexpected content

  • Use live model ids
  • Chat needs valid messages; social-data needs business fields
  • Video poll: GET /v1/video/generations/{task_id} only — not /v1/videos/*/content for Omni Flash / MiniMax creates

​
Cannot connect

  • Firewall/proxy TLS to api.omnimux.ai
  • Many OpenAI SDKs need base ending with /v1
  • Probe with GET /v1/models