Skip to main content
provider_rejected_request means the model service refused the call OpenType made for a verdict run. Read this page if a verdict run fails with this code.

What happened

Route: POST /v1/runs. Route detail: verdict runs only. For a decision run the same refusal answers decision_unavailable. The model service refused the request as invalid, after your request had already passed OpenType’s own checks. Neon 1.1 does not serve verdict runs; today every verdict run is refused earlier with no_route_available. Every provider_* code has the same message, “the provider call failed”. Branch on code, never on the message. The message never contains model output. If this was the first model call, the run was refused before the model served it. You are not charged, and the hold is released, but the run stays pending: a replay with the same Idempotency-Key returns 202 with "state": "pending". If an earlier call in the same run was served (a verdict repair), the run is settled failed and a replay returns 200 with "state": "failed". In both cases, retry with a new key.

How to fix

  • Retry once with a new Idempotency-Key.
  • If it repeats, report the request_id.

Example

A retry loop with backoff and a new key per attempt:
  • Verdict runs - the verdict contract and its limits.
  • Error handling - a status-to-action table and a retry helper for every error.
  • Idempotency - when to reuse an Idempotency-Key and when to send a new one.
  • Request ids - send your own x-request-id and quote it when you report a problem.
  • Problem codes - every code, its status, and whether a retry can help.