Vora Compute

Errors

Errors use the OpenAI shape. OpenAI SDKs raise their usual exceptions.

{
  "error": {
    "message": "Invalid API key. Create one at https://inference.voracompute.com/console/keys.",
    "type": "authentication_error",
    "param": null,
    "code": "invalid_api_key"
  }
}

Codes

StatusCodeMeaningRetry
400invalid_jsonThe body is not valid JSON.Don't retry
400invalid_requestA parameter is missing or has the wrong type.Don't retry
400context_length_exceededInput plus output exceed the selected model's context window.Don't retry
400unsupported_parameterWe don't support this parameter, e.g. n > 1 or logit_bias.Don't retry
400unsupported_contentThis model does not support the supplied content type.Don't retry
400invalid_imageUse valid JPEG, PNG or WebP data URLs, within the model's image limits.Don't retry
400image_limit_exceededMore images or decoded image data than the model allows (vision_limits in /v1/models).Don't retry
401missing_api_keyNo Authorization: Bearer header.Don't retry
401invalid_api_keyThe key does not exist.Don't retry
403key_revokedThe key was revoked. Create a new one.Don't retry
403account_disabledThe account is disabled. Contact us.Don't retry
403access_revokedAccess was revoked while the request was queued.Don't retry
403pilot_access_requiredThis account has no active plan or pilot access.Don't retry
413request_too_largeThe request body is too large.Don't retry
404model_not_foundUnknown model. See GET /v1/models.Don't retry
404unknown_endpointUse chat completions or the model catalog.Don't retry
429concurrency_limitThe account's admitted-request limit has been reached.Retry with backoff
429account_concurrencyThe account has reached the model's admitted-request limit across keys and Chat.Retry with backoff
429account_pool_concurrencyThe account already has a request admitted to this model pool.Retry with backoff
429large_request_limitThe account already has a long-context request admitted.Retry with backoff
500internal_errorSomething failed on our side.Retry with backoff
503model_unavailableThe model is offline or loading.Retry with backoff
503engine_busyThe model is at capacity.Retry with backoff
503model_timeoutThe request exceeded a time limit while waiting or generating a response.Retry with backoff
503stream_interruptedThe model stopped mid-reply.Retry with backoff

When to retry

Rate-limit headers

Requests receive x-request-id without per-minute token quota headers. Per-account concurrency limits return 429 with Retry-After; a full model returns 503 with Retry-After. The legacy quota headers below are retained only as a reference for older clients.

HeaderMeaning
x-ratelimit-limit-requestsRequests allowed per minute.
x-ratelimit-remaining-requestsRequests left in the current minute.
x-ratelimit-reset-requestsTime until the minute resets, e.g. 12s.
x-ratelimit-limit-tokensTokens allowed per day.
x-ratelimit-remaining-tokensTokens left today.
x-request-idThis request's id. Include it when you contact us.

Errors in a stream

If the model stops unexpectedly during a stream, the last event is an error, not [DONE]:

data: {"error":{"message":"The model stopped unexpectedly. Retry the request.","type":"server_error","param":null,"code":"stream_interrupted"}}

Check each event for an error field before you read choices.