青峰智影青峰智影
API ReferenceMirava
AI Model APIVideosSeedance Format

Common Errors and Troubleshooting

Common error codes, causes, and handling during Seedance video generation integration.

Error Quick Reference

Error Code / MessageCauseHandling
401 unauthorizedapi_key invalid or not providedCheck the Authorization: Bearer header
400 invalid modelWrong model codeVerify the code in the model list
400 group mismatchGroup does not match the channel familyConfirm the group the api_key belongs to
400 invalid durationDuration outside the model's supported rangeRefer to the duration tiers in the parameters table
400 invalid resolutionUnsupported resolutionRefer to the resolution tiers in the parameters table
400 invalid ratioUnsupported aspect ratioUse a supported ratio or adaptive
400 asset not activeAsset not finished processing or expiredWait for the asset to become active, or re-upload
413 Payload Too LargeRequest body too largeUse asset library references instead of embedding large files
429 rate limitedToo many requestsLower the polling frequency and apply backoff retries
500 upstream errorUpstream channel errorRetry later, or switch groups

Troubleshooting Order

  1. Confirm the model matches the group — choosing the wrong group is the most common cause of failure.
  2. Confirm parameters are within the supported range — resolution / duration / ratio must all satisfy the model constraints simultaneously.
  3. Confirm the asset status is active — assets in processing or failed are unavailable.
  4. Confirm the asset matches the channel family — cross-family references always fail.
  5. Check the request body size — when over the limit, prefer asset library references over inline embedding.

Typical Integration Flow

  1. Create an asset library and upload image / video / audio assets.
  2. Poll the asset status until it becomes active.
  3. Call POST /v1/video/generations to submit the generation task and record the task_id.
  4. Poll GET /v1/video/generations/{task_id} until succeeded.
  5. Read video_url to download the video; if return_last_frame is enabled, save the last frame as well.
  6. If the moderation result is needed, call POST /api/generation/video/moderation-result.
  7. Clean up unused assets as needed.

How is this guide?