# Errors > The error envelopes, status codes and error codes the API returns, and how to fix each. Errors from the endpoints that reach a model, and from Key, carry `x-request-id`. Quote it when you contact support. A request that Deference forwarded to a provider appears in [Activity](https://deference.si/docs/dashboard/activity) under that id, including one the provider failed. A request that Deference refused before forwarding it, with a 400, 401, 402, 404, 413, 429 or 503 of its own, does not appear there. `GET /v1/models/{id}` answers an unknown model with a 404 that carries no request id. ## OpenAI envelope Chat completions, Responses, Embeddings, Images, Models and Key return this shape. ```json { "error": { "message": "This account has no credit left. Add credit in the dashboard to continue.", "type": "insufficient_credit", "code": "insufficient_credit", "param": null } } ``` ## Anthropic envelope Messages returns this shape, which Claude Code parses. ```json { "type": "error", "error": { "type": "billing_error", "message": "This account has no credit left. Add credit in the dashboard to continue." }, "request_id": "req_01K7Z4F2XQ" } ``` ## Status and type | Status | OpenAI `type` | Anthropic `type` | | -------- | ----------------------- | ----------------------- | | 400 | `invalid_request_error` | `invalid_request_error` | | 401 | `authentication_error` | `authentication_error` | | 402 | `insufficient_credit` | `billing_error` | | 403 | `permission_error` | `permission_error` | | 404 | `invalid_request_error` | `not_found_error` | | 413 | `invalid_request_error` | `request_too_large` | | 429 | `rate_limit_error` | `rate_limit_error` | | 502, 504 | `api_error` | `api_error` | | 503 | `api_error` | `overloaded_error` | ## Codes Codes are in `error.code` in the OpenAI envelope. The Anthropic envelope carries the type only. | Status | Code | Cause | Fix | | ------ | ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------- | | 400 | `invalid_json` | The body is not valid JSON | Send a JSON object | | 400 | `missing_model` | The request has no `model` | Add a model id | | 400 | `invalid_parameter` | Images: `n` is not a whole number from 1 to 10 | Send a valid `n` | | 400 | `unsupported_parameter` | The body sets `models`, `route` or `provider`, a `plugins` entry that adds a fee, X search or audio input, or sends a file to a model without file input and no free parser | Name one model and drop those fields. For files, add the `cloudflare-ai` parser or pick a model with file input | | 400 | `unsupported_model` | The model bills per search or per song, such as `perplexity/sonar-deep-research` and the Lyria models | Use another model | | 401 | `missing_api_key` | No key was sent | Send `Authorization: Bearer sk-df-...` or `x-api-key` | | 401 | `invalid_api_key` | The key is not recognized | Copy the key again, or create a new one | | 401 | `api_key_disabled` | The key is disabled | Enable it in API keys, or use another key | | 401 | `api_key_expired` | The key passed its expiry | Create a new key | | 402 | `insufficient_credit` | The account has no available credit, or less than the request's hold. A file, image or video given as a URL is held at the model's whole context window | Add credit, lower `max_tokens`, or send fewer URL inputs | | 402 | `key_limit_reached` | The key hit its credit limit, or has less left than the request's hold | Raise the limit, lower `max_tokens` or use another key | | 402 | `free_credit_not_eligible` | The account has only free credit, and this model or request does not qualify | Use an open-weight text model, set a lower `max_tokens`, or add credit | | 404 | `model_not_found` | The model id is not in the catalog | List models and pick a current id | | 413 | `request_too_large` | The body is over 32 MB, or 64 MB on Images | Send a smaller body | | 429 | `rate_limited` | Too many requests in a minute | Wait for `retry-after` seconds | | 429 | `too_many_concurrent_requests` | 8 requests are already running on the key | Retry when one finishes | | 502 | `upstream_error` | The model provider returned an error | Retry the request | | 503 | `service_unavailable` | Inference is temporarily unavailable | Retry shortly | | 504 | `upstream_timeout` | The provider did not answer in time: 15 minutes for a call that is not streamed, 120 seconds for Images. The call may still have run, so the credit held for it is charged | Retry, or stream the request | `free_credit_not_eligible` explains itself: its message lists what free credit pays for and suggests `max_tokens`. See [Free credit](https://deference.si/docs/concepts/free-credit). ## Provider errors Errors that describe your request pass through from the provider: `400`, `403`, `404`, `408`, `413`, `422` and `429`. Anthropic-format bodies are returned unchanged. A provider `401` or `402`, which concerns Deference's own upstream account, returns `503`. Any other provider failure returns `502`. Both carry your request id and never reveal the upstream account. ## Failures after a stream starts A stream that fails midway still returns HTTP `200`, and the error arrives as an event in the stream. Activity marks that request failed. A failed request is charged only for what the provider reports. See [Streaming events](https://deference.si/docs/api-reference/streaming-events). ## Retry Retry `429`, `502`, `503` and `504` with backoff, and honor `retry-after` when present. It is a whole number of seconds. Do not retry `400`, `401`, `402`, `404` or `413` until you fix the cause. See [Rate limits](https://deference.si/docs/api-reference/rate-limits).