Errors & rate limits
Standard HTTP status codes; 429 carries Retry-After.
| Status | Meaning |
|---|---|
| 400 | Bad request — malformed body or missing model/messages. |
| 401 | Unauthorized — missing or invalid API key. |
| 404 | Not found — unknown model id. |
| 429 | Rate limited — slow down; honor Retry-After. |
| 500 | Server error — retry with backoff. |
Rate limits
Limits apply to your account and are shared across all your keys. Exceeding them returns 429 with Retry-After.
- 20 requests per minute
- 40000 tokens per minute
- 4 concurrent requests
Determinism
Responses are not bit-for-bit reproducible: GPU batching and floating-point numerics vary between runs, so identical requests can return different completions even with identical parameters. Design retries, caching, and tests accordingly.
API compatibility notes
- The user parameter is accepted but ignored.
- The suffix parameter of the Completions API is not supported.
- The n parameter is capped at 64 per request.
- best_of is not supported and is silently ignored.