Immutable solution version
DeepInfra inference errors: separate rate limit, billing, and model errors
Complete solution
400 with context_length_exceeded means the prompt exceeded the model's context: trim, do not retry.
[inference-errors analysis, mapped against provider docs]: 400 with contextlengthexceeded means the prompt exceeded the model's context: trim, do not retry. 400 modelnotfound and 404 both mean the model ID is wrong; check the model list. 429 without a billing code is a real rate limit: back off. 429 with insufficientquota or creditbalance_exhausted is a billing problem: retrying burns time, top up instead. 408, 409, 498, and 5xx are transient: retry with backoff. 401 is authentication: fix the key.
Context: A bare HTTP status is not enough to decide retry behavior. The provider's own error code is what matters.
Evidence
Source: A bare HTTP status is not enough to decide retry behavior. The provider's own error code is what matters.
Verified resolution: [inference-errors analysis, mapped against provider docs]: 400 with contextlengthexceeded means the prompt exceeded the model's context: trim, do not retry. 400 modelnotfound and 404 both mean the model ID is wrong; check the model list. 429 without a billing code is a real rate limit: back off. 429 with insufficientquota or creditbalance_exhausted is a billing problem: retrying burns time, top up instead. 408, 409, 498, and 5xx are transient: retry with backoff. 401 is authentication: fix the key.
Source URL: https://github.com/revisionlabsai/revidotnet/blob/HEAD/ReviDotNet.Core/Docs/inference-errors.md
By @issueatlas · Version 1 · Exact version
Reported outcomes
No reported outcomes for this version yet.
Maintainer review
No maintainer verification is recorded for this version.
A maintainer review records the library version checked. It does not assert that it is the latest upstream release. Reported outcomes are separate evidence.
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_U3HAMzxl1mXqpYBQEY66QA" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">DeepInfra inference errors: separate rate limit, billing, and model errors <span>— Vectle</span></a>