Create video generation task

Submit a video generation task; returns a task ID immediately. Video generation is an async operation -- poll task status via GET /v1/videos/generations/{taskId}.

Billing: estimated amount is frozen at submission based on duration; settled by actual usage on success. Frozen amount is refunded on failure.

Supports multiple input modes (specified via the content array):

• Text-to-video: Only pass a type: text prompt
• Image-to-video (first frame / first+last frame): Pass images with role set to first_frame / last_frame
• Multi-modal reference video (Seedance 2.0 / MiniMax-H3): reference images, videos, and audio
• Audio-enabled video (Seedance 2.0, 1.5 pro): Set generate_audio: true. MiniMax-H3 does not support this field.
• Draft mode (Seedance 2.5 only): draft: true first renders a 480p preview, billed the same as a normal 480p video. After review, submit again with only a draft_task item in content and the returned task ID to render the 1080p final video. Do not resend the prompt, references, duration, aspect ratio, seed, or generate_audio. The two steps are billed separately. The final video's price follows whether the draft step included a reference video; the draft itself is not an input video. The draft task ID is valid for 7 days. Idle models do not support this.

MiniMax-H3 (China / international): see "MiniMax H3 request parameters". resolution is 768P or 2K, duration is an integer 4–15, text-to-video requires a concrete ratio, and first/last frames cannot mix with reference assets.

Image / media reference rules (important):

• Regular images: image_url.url must be a publicly reachable https URL (object storage / CDN). The upstream engine fetches the URL directly; the proxy does not buffer the image.
• Reference images that contain real people: must use asset://<asset_id>, pointing to a verified real-person asset. Complete the H5 liveness verification flow via POST /v1/asset-groups/validate-session first to obtain a group_id/asset_id. Passing a real-person image as a URL or inline base64 will be rejected upstream with InputImageSensitiveContentDetected.PrivacyInformation.
• Do not inline base64: data:image/...;base64,... data URIs bloat the request body to MB scale. The request body is hard-capped at 5 MB; exceeding it returns 413 payload_too_large. Upload to object storage and pass a URL, or use asset:// from the asset library.

Set video_url_mode to upstream to receive the native output without waiting for archiving, auto to permit a saved-copy fallback, or tos to wait for a verified archive. Omitting it preserves the account default. This setting applies to the new task and its callbacks; it does not disable background saving. Native expiry may be unknown, and idle enhanced models reject upstream.

To combine an explicit mode with callback_url, configure the account Webhook Secret first; otherwise creation returns 400 webhook_secret_required. Existing callbacks without a secret keep their previous provider delivery path when the mode is omitted.

Authorization: Bearer tr-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

curl -X post "https://api.xrtoken.ai/v1/videos/generations" \  -H "Content-Type: application/json" \  -d '{    "model": "volcengine/doubao-seedance-2-0-260128",    "content": [      {        "type": "text",        "text": "A cat running on the grass, cinematic, slow motion"      }    ],    "resolution": "720p",    "duration": 5  }'

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "upstream_id": "string",
  "model": "string",
  "status": "queued",
  "created_at": "2019-08-24T14:15:22Z"
}

{
  "error": "model field is required",
  "type": "invalid_request_error"
}

{
  "error": "invalid or missing API key",
  "type": "auth_error"
}

{
  "error": "insufficient balance -- please top up or upgrade your plan",
  "type": "billing_error"
}

{
  "error": "rate limit exceeded",
  "type": "rate_limit_error"
}

{
  "error": "upstream provider error",
  "type": "server_error"
}