Video Edit

Seedance 2.5 changes an existing video as your prompt says, for example replacing an object or changing the style, optionally with reference images. The output keeps the length and aspect ratio of the video you edit.

Create a task

Use the shared create endpoint with model: "seedance-2.5". It usually responds in under 1 second and the cost is frozen within a few seconds; the video usually takes several minutes. Get the result once the task has finished.

Headers

Body

duration and aspect_ratio aren't accepted (the output follows the video you edit), and neither are video_urls and audio_urls: sending any of them returns 400 invalid_request with param set to it (for example duration is not allowed for mode video_edit; the output is as long as the source video).

Output length and billing

• Output length: about as long as the video you edit, sometimes slightly shorter (a 4-second video gives about 3.7 seconds).
• Billed seconds: the output length rounded up to a whole second; less than 0.05 seconds over doesn't count (10.02 s is billed as 10 seconds, 10.06 s as 11). The 3.7-second output above is billed as 4.
• Billing: 30 × the price per second is frozen first; when the task succeeds, the billed seconds are charged and the rest returned, see Pricing.
• Balance: your available balance (and the key's spend limits) must cover the 30 seconds, even if the video is shorter; otherwise the task fails with insufficient_balance (or spend_limit_exceeded).

Replace the car in the video with the one in the reference image, 720p:

curl https://api.nanoapi.ai/v1/tasks \
  -H "Authorization: Bearer $NANOAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5",
    "mode": "video_edit",
    "video_url": "https://example.com/source.mp4",
    "image_urls": ["https://example.com/car.jpg"],
    "prompt": "Edit @Video1: replace the car with the one in @Image1",
    "resolution": "720p"
  }'

Response: 200 OK. data is the newly created task, with only these fields; each one is described in Create a task: Response. Keep data.id to get the result: once the task succeeds, the video is at data.outputs[0].url of the retrieved task or the webhook. The task can still fail after it's created (for example a file can't be downloaded), so go by what retrieving the task or the webhook tells you.

{
  "code": 200,
  "message": "success",
  "data": {
    "object": "task",
    "id": "tk_01jbd2s8x4c6v9b3n5m7q1w4e8",
    "model": "seedance-2.5",
    "status": "queued",
    "error": null,
    "created_at": "2026-10-31T08:30:00Z"
  }
}

Pricing

cost = billed seconds of the output × price per second of the resolution

Loading the current prices…

Example: the request above freezes 30 × the video_edit 720p price per second first. When the task succeeds, the billed seconds × the price per second are charged and the rest returned: for a 10-second output, 10 seconds are charged and 20 returned. billing.billed_seconds is then the billed output length. If the task fails, all of it is returned.

video_edit has its own price per second, separate from the other modes. Prices change, so read the current ones from GET /v1/products (the prices rows whose mode is this mode) instead of hard-coding them; billing.frozen and billing.charged on the retrieved task are what count. All Seedance 2.5 prices: Seedance 2.5 → Pricing.

Errors

Create request errors: the request fails with an HTTP error and no task is created. Specific to this mode:

Other errors of the create endpoint (401, 402, 429 and so on): Create a task → Errors.

Task failures: the create request succeeded (200) and the task later turned failed. There's no HTTP status: the reason is the task's error.type, from retrieving the task or the webhook.

Failure reasons shared by every mode (such as a balance too low for the task): Seedance 2.5 → Errors; all of them: Failure reasons.