Errors

Each chat endpoint returns errors in the same shape as the API standard it is compatible with (OpenAI, Anthropic, or Gemini). Every error response also includes an X-Request-Id header, and returns only the information you need to debug your request.

OpenAI — `/v1/chat/completions` (and image/video endpoints)

{
  "error": {
    "message": "Insufficient credits",
    "type": "insufficient_quota",
    "code": "insufficient_credits",
    "param": null
  }
}

Anthropic — `/v1/messages`

{
  "type": "error",
  "error": {
    "type": "authentication_error",
    "message": "Invalid API key"
  }
}

Gemini — `/v1beta/models/{model}:generateContent`

{
  "error": {
    "code": 400,
    "message": "model is required",
    "status": "INVALID_ARGUMENT"
  }
}

Status mapping

The error type / status is derived from the HTTP status:

HTTP	OpenAI `type`	Anthropic `type`	Gemini `status`
400	invalid_request_error	invalid_request_error	INVALID_ARGUMENT
401	authentication_error	authentication_error	UNAUTHENTICATED
403	permission_error	permission_error	PERMISSION_DENIED
404	not_found_error	not_found_error	NOT_FOUND
402	insufficient_quota	invalid_request_error	RESOURCE_EXHAUSTED
429	rate_limit_error	rate_limit_error	RESOURCE_EXHAUSTED
5xx	api_error	api_error / overloaded_error	SERVER_ERROR / UNAVAILABLE

Model parameter rejections

When a model does not accept a value in your request, the endpoint returns HTTP 400 with the model’s own explanation. Reasoning settings use the code invalid_reasoning_effort, and the message lists the values that model accepts, so the request can be corrected without guessing. Each model’s accepted reasoning levels, its default and whether reasoning can be disabled are published in GET /v1/models under capability_metadata.reasoning. Rate limiting returns 429, and a request that exceeds the time budget returns 504. A 502 means the platform could not obtain a usable answer from the model after retrying — it is not a verdict on your parameters, so read the response body before changing them.

Media generation errors and retries

For image and video generation, use the structured error.code and the task’s status (task.status in your client) to decide what to display and whether to retry.

Error code	Meaning and recommended action
`not_found`	In a generation task, this may mean no valid media was returned, or the requested endpoint or resource does not exist. It does not establish a content-policy violation.
`rate_limit`	The request may be rate-limited or the model service may be temporarily overloaded. Wait, then retry a limited number of times with increasing delays.
`content_policy`, `content_filter`, `image_safety`	An explicit content-policy rejection. Ask the user to revise the content.

Only suggest content changes for an explicit policy code or a clear content-policy refusal. A message merely mentioning safety, or HTTP 502 alone, is not evidence of a policy violation. If an asynchronous task is still pending or processing, continue querying /v1/tasks/{task_id} with the same task_id; do not submit a duplicate generation request.

Minor-sensitive media prompts

Image and video requests are rejected with HTTP 400 and code content_policy when a prompt clearly combines a minor with exposure or emphasis of sensitive body areas, or with explicit sexual or nudity content. This check happens before task creation and credit reservation, so no credits are charged.

{
  "error": {
    "message": "Requests involving minors and exposure or emphasis of sensitive body areas are not allowed. Use an adult subject (18+), remove sensitive-body close-ups, and keep the subject fully clothed. No credits were charged.",
    "type": "invalid_request_error",
    "code": "content_policy",
    "param": null
  }
}

Ordinary child-safe scenes such as family, classroom, sports, and art prompts are not blocked by this targeted preflight rule. Requests that pass preflight remain subject to each model’s general safety policy.

Get started

Integrations

Core APIs

Operations

OpenAI — `/v1/chat/completions` (and image/video endpoints)

Anthropic — `/v1/messages`

Gemini — `/v1beta/models/{model}:generateContent`

Status mapping

Model parameter rejections

Media generation errors and retries

Minor-sensitive media prompts

​OpenAI — /v1/chat/completions (and image/video endpoints)

​Anthropic — /v1/messages

​Gemini — /v1beta/models/{model}:generateContent

​Status mapping

​Model parameter rejections

​Media generation errors and retries

​Minor-sensitive media prompts

OpenAI — `/v1/chat/completions` (and image/video endpoints)

Anthropic — `/v1/messages`

Gemini — `/v1beta/models/{model}:generateContent`

Status mapping

Model parameter rejections

Media generation errors and retries

Minor-sensitive media prompts