Seedance Video API Reference | Nano Banana Pro API

Seedance

ByteDance Seedance video generation with optional audio generation

Endpoint: POST /api/v1/videos/generate
model: seedance
Output: Video
Credits: from 8

Submit a task

POST/api/v1/videos/generate

Parameters

modelstringRequired
"seedance", "seedance2", or "seedance2-fast"
seedanceseedance2seedance2-fast
typestringOptionalDefault text-to-video
"text-to-video" or "image-to-video" (default: text-to-video)
text-to-videoimage-to-video
promptstringRequired
Text prompt (3-2500 chars)
image_urlsstring[]Optional
Required for image-to-video; supports 1-2 images
media_urlsstring[]Optional
Seedance2 media references. Supports images, videos, and audio; audio must be paired with at least one image or video. Video and audio are billed per second by their length, which is measured when you submit.
input_imagestringOptional
Deprecated. Alias for image_urls[0]
aspect_ratiostringOptional
"1:1", "21:9", "4:3", "3:4", "16:9", or "9:16"
1:121:94:33:416:99:16
durationstringOptional
"4", "8", or "12" for seedance; seedance2 supports 4-15 seconds
4812
resolutionstringOptional
"480p" or "720p" for seedance; seedance2 also supports "1080p". "4k" requires model "seedance2" (other models reject "4k").
480p720p1080p4k
fixed_lensbooleanOptionalDefault false
Use fixed camera/lens behavior (default: false)
truefalse
generate_audiobooleanOptionalDefault true
Generate synchronized audio (default: true). Set to false for silent video.
truefalse

Seedance prompt guide

Seedance prompts work best as concrete director instructions. Describe the subject, action, scene, camera motion, visual style and constraints, then say what each reference file is for.

For image-to-video, the first image is the opening frame and an optional second image is the closing frame. For reference media, pass images, videos and audio in media_urls.
Describe each reference's role in the prompt in plain words ("the supplied cup", "the camera move from the supplied video"); do not refer to files by number or id.
For edits say "strictly edit the supplied source video"; to continue a clip say "continue from the supplied previous clip".
For complex scenes, list the shots in order, then a style and constraint package: stable faces, natural motion, no deformation, no watermark, no logo and no subtitles unless intended.

Request

curl -X POST https://www.bananapro.site/api/v1/videos/generate \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance",
    "type": "text-to-video",
    "prompt": "A cinematic pan across a rainy neon street",
    "aspect_ratio": "16:9",
    "duration": "8",
    "resolution": "720p",
    "generate_audio": true
  }'

Response200

JSON

{
  "success": true,
  "data": {
    "task_id": "task_seedance123",
    "credits_used": 64,
    "remaining_credits": 436,
    "model": "seedance"
  }
}

The credits_used values shown in these examples are illustrative. Actual usage is calculated when you submit and returned by the API.

Query the task

GET/api/v1/videos/{task_id}

status

pending: Accepted and waiting to start. Keep polling.
processing: Running. Keep polling.
completed: Finished. Read video_url; output holds the full result.
failed: Ended without a result. error_message says why and credits_refunded shows what was returned.

Poll every 5 to 10 seconds and stop at completed or failed, or register a webhook to be notified instead. Failed tasks are refunded automatically.

Request

curl https://www.bananapro.site/api/v1/videos/task_abc123 \
  -H "Authorization: Bearer sk-your-api-key"

Response200

JSON

{
  "success": true,
  "data": {
    "task_id": "task_abc123",
    "model": "seedance",
    "status": "completed",
    "output": { "video_url": "https://..." },
    "video_url": "https://...",
    "error_message": null,
    "credits_used": 64,
    "credits_refunded": 0,
    "created_at": "2026-10-04T10:00:00.000Z",
    "updated_at": "2026-10-04T10:01:12.000Z",
    "completed_at": "2026-10-04T10:01:12.000Z"
  },
  "request_id": "req_abc123"
}

Wait for the result

TASK_ID=task_abc123
while true; do
  TASK=$(curl -s https://www.bananapro.site/api/v1/videos/$TASK_ID \
    -H "Authorization: Bearer sk-your-api-key")
  STATUS=$(echo "$TASK" | jq -r '.data.status')
  if [ "$STATUS" = "completed" ] || [ "$STATUS" = "failed" ]; then
    echo "$TASK" | jq
    break
  fi
  sleep 10
done

Pricing

Duration	480p No Audio	480p Audio	720p No Audio	720p Audio
4 sec	8	16	16	32
8 sec	16	32	32	64
12 sec	24	48	48	96

Seedance 2 4K (resolution "4k") requires model "seedance2", durations 4-15s, billed per second at ~117 credits/sec (e.g. 5s ≈ 585 credits).

Features

Text-to-video generation
Image-to-video generation
Optional audio generation
Seedance 2 supports 4K output

curl -X POST https://www.bananapro.site/api/v1/videos/generate \ -H "Authorization: Bearer sk-your-api-key" \ -H "Content-Type: application/json" \ -d '{ "model": "seedance", "type": "text-to-video", "prompt": "A cinematic pan across a rainy neon street", "aspect_ratio": "16:9", "duration": "8", "resolution": "720p", "generate_audio": true }'

{ "success": true, "data": { "task_id": "task_abc123", "model": "seedance", "status": "completed", "output": { "video_url": "https://..." }, "video_url": "https://...", "error_message": null, "credits_used": 64, "credits_refunded": 0, "created_at": "2026-10-04T10:00:00.000Z", "updated_at": "2026-10-04T10:01:12.000Z", "completed_at": "2026-10-04T10:01:12.000Z" }, "request_id": "req_abc123" }

TASK_ID=task_abc123 while true; do TASK=$(curl -s https://www.bananapro.site/api/v1/videos/$TASK_ID \ -H "Authorization: Bearer sk-your-api-key") STATUS=$(echo "$TASK" | jq -r '.data.status') if [ "$STATUS" = "completed" ] || [ "$STATUS" = "failed" ]; then echo "$TASK" | jq break fi sleep 10 done

Duration

480p No Audio

480p Audio

720p No Audio

720p Audio

4 sec

8 sec

12 sec