Retry only transient failures
Use bounded exponential backoff, respectRetry-After, and stop after a fixed attempt or time budget.
Retry conditions
Do not retry authentication, billing, validation, missing-model, or malformed-request errors until the request is corrected.
Wait for a cold model
A model that has not served for a while goes cold. The next call starts it and gets425 until it is ready, which can take several minutes.
To wait instead of retrying, send X-Fastino-Wait-For-Model: true on POST /v1/chat/completions, /v1/messages, /v1/responses, /v1/systemone, or /v1/gliner-2. The request waits up to 150 seconds for the model, then runs. If the model is still starting after that, you get the usual 425 with Retry-After, and the model keeps starting for your retry. The header accepts true, 1, or yes in any case; any other value is ignored. Streaming requests ignore this header.
Check and warm a model before use
GET /v1/model-status/{model_id}returnsstate(ready,starting, orcold) andretry_after_seconds, which isnullonce the model is ready.POST /v1/model-status/{model_id}/warmstarts the model without running inference and returns202. It is not billed, and repeated calls share one start.
retry_after_seconds until it is ready. Each API server reports what it has seen, so right after a warm call the status can still say cold for a short time; keep polling.
Safe retry checklist
- Use an idempotency key for training-job creation and other supported mutations.
- Keep the same request body when replaying an idempotent request.
- Apply jitter and a maximum delay.
- Log the final status and request ID, but never the API key.

