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
| Status | Code | Meaning | Retry |
|---|---|---|---|
| 400 | invalid_json | The body is not valid JSON. | Don't retry |
| 400 | invalid_request | A parameter is missing or has the wrong type. | Don't retry |
| 400 | context_length_exceeded | Input plus output exceed the selected model's context window. | Don't retry |
| 400 | unsupported_parameter | We don't support this parameter, e.g. n > 1 or logit_bias. | Don't retry |
| 400 | unsupported_content | This model does not support the supplied content type. | Don't retry |
| 400 | invalid_image | Use valid JPEG, PNG or WebP data URLs, within the model's image limits. | Don't retry |
| 400 | image_limit_exceeded | More images or decoded image data than the model allows (vision_limits in /v1/models). | Don't retry |
| 401 | missing_api_key | No Authorization: Bearer header. | Don't retry |
| 401 | invalid_api_key | The key does not exist. | Don't retry |
| 403 | key_revoked | The key was revoked. Create a new one. | Don't retry |
| 403 | account_disabled | The account is disabled. Contact us. | Don't retry |
| 403 | access_revoked | Access was revoked while the request was queued. | Don't retry |
| 403 | pilot_access_required | This account has no active plan or pilot access. | Don't retry |
| 413 | request_too_large | The request body is too large. | Don't retry |
| 404 | model_not_found | Unknown model. See GET /v1/models. | Don't retry |
| 404 | unknown_endpoint | Use chat completions or the model catalog. | Don't retry |
| 429 | concurrency_limit | The account's admitted-request limit has been reached. | Retry with backoff |
| 429 | account_concurrency | The account has reached the model's admitted-request limit across keys and Chat. | Retry with backoff |
| 429 | account_pool_concurrency | The account already has a request admitted to this model pool. | Retry with backoff |
| 429 | large_request_limit | The account already has a long-context request admitted. | Retry with backoff |
| 500 | internal_error | Something failed on our side. | Retry with backoff |
| 503 | model_unavailable | The model is offline or loading. | Retry with backoff |
| 503 | engine_busy | The model is at capacity. | Retry with backoff |
| 503 | model_timeout | The request exceeded a time limit while waiting or generating a response. | Retry with backoff |
| 503 | stream_interrupted | The model stopped mid-reply. | Retry with backoff |
When to retry
429: wait for theRetry-Afterheader, in seconds, then retry.500and503: respectRetry-Afterand use exponential backoff.- Other
4xx: don't retry. Fix the request.
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.
| Header | Meaning |
|---|---|
x-ratelimit-limit-requests | Requests allowed per minute. |
x-ratelimit-remaining-requests | Requests left in the current minute. |
x-ratelimit-reset-requests | Time until the minute resets, e.g. 12s. |
x-ratelimit-limit-tokens | Tokens allowed per day. |
x-ratelimit-remaining-tokens | Tokens left today. |
x-request-id | This 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.