Errors & Rate Limits

Error Format

All errors return a consistent JSON format:

{
  "success": false,
  "error": "Human-readable error message",
  "code": "ERROR_CODE"
}

Status	Meaning
200	Success
201	Created (new API key)
400	Bad request (missing/invalid params)
401	Unauthorized (invalid or missing API key)
403	Forbidden (insufficient permissions)
404	Not found
429	Rate limited
500	Server error

Code	Description
`INVALID_API_KEY`	API key is invalid, expired, or revoked
`INSUFFICIENT_CREDITS`	Not enough credits for this generation
`MISSING_FIELDS`	Required fields are missing
`GENERATION_ERROR`	The generation failed to start
`MODEL_NOT_FOUND`	The specified model doesn't exist
`RATE_LIMITED`	Too many requests

When rate limited, the response includes:

{
  "status": false,
  "message": "Too many requests, please try again later"
}

When polling status, the state field can be:

State	Description
`pending`	Generation is queued (Creative Director only)
`processing`	Generation is in progress
`completed`	Generation finished, `result` field contains URLs
`failed`	Generation failed, `error` field explains why
`cancelled`	Generation was cancelled

Chat (POST /v1/chat): requires polling, typically 5-30 seconds
Image: typically completes within 30 seconds
Video: typically completes within 5 minutes
Music: typically completes within 2 minutes
Speech/Sound: typically completes within 30 seconds
Creative Director: typically completes within 3 minutes (depends on scene count)

If polling beyond these times, the generation may have failed silently. Check the status one final time, then consider retrying.