Operating guidance
How the API behaves around a request: what a limit means, which errors to retry, what is charged when an attempt fails, how to make a retry safe, how a stream ends, what happens to your data, and which rows of the contract have been validated.
| Page | Carries |
|---|---|
| Limits | Rate limits per key and plan, the headers, what 429 means; no number until decided |
| Errors | Every error type with when it occurs and what to do; only 503 and 500 are ever 5xx |
| Retries and billing outcomes | What is charged when an attempt fails, is interrupted, times out or is retried |
| Idempotency | The idempotency-key header on the task and job routes; what a repeat answers |
| Streaming | Server-sent events on chat completions, cancellation, where the cost of a streamed answer arrives |
| Data handling | Weights versus request data, the request-data policy by plan, pools and runtime access, regions |
| Compatibility matrix | Status per endpoint, per model and per client version; every cell unvalidated at launch |
- Page
- Limits
- Carries
- Rate limits per key and plan, the headers, what 429 means; no number until decided
- Page
- Errors
- Carries
- Every error type with when it occurs and what to do; only 503 and 500 are ever 5xx
- Carries
- What is charged when an attempt fails, is interrupted, times out or is retried
- Page
- Idempotency
- Carries
- The
idempotency-keyheader on the task and job routes; what a repeat answers
- Page
- Streaming
- Carries
- Server-sent events on chat completions, cancellation, where the cost of a streamed answer arrives
- Page
- Data handling
- Carries
- Weights versus request data, the request-data policy by plan, pools and runtime access, regions
- Carries
- Status per endpoint, per model and per client version; every cell unvalidated at launch
Related sheets
- Sheet
- 12 of 13
- Updated
- 2026-10-21
- Status
- Preview