Public API

Generate video and images from your own tools

Create a key, call the API with Bearer auth, and poll task status until your result is ready. Works with Claude Code, Codex, and any HTTP client.

Manage keys

Quickstart

Step 1

Create a key

Generate an API key in your dashboard. It is shown once, so store it somewhere safe.

Step 2

Call the API

Send a POST request with your Bearer key and an Idempotency-Key header.

Step 3

Poll the result

Poll the task status endpoint until the status is completed or failed, then read the output.

Authentication

Every request is authenticated with a Bearer API key in the Authorization header.

http

Authorization: Bearer sk_live_your_api_key
Content-Type: application/json
Idempotency-Key: a-unique-id-per-request

Seedance 2 Video

Text, image, or media to video.

Submit a job

POST

/api/v1/video/seedance2

Parameters

Parameter	Type	Required	Default	Allowed values
`mode` Generation mode.	`string`	Optional	`text-to-video`	`text-to-videoimage-to-videomedia-to-video`
`quality_tier` Quality tier.	`string`	Optional	`standard`	`ministandardpro`
`channel` Rendering channel.	`string`	Optional	`standard`	`standardrealwild`
`prompt` Text prompt.	`string`	Required	`—`	`3–10000 chars`
`aspect_ratio` Aspect ratio.	`string`	Optional	`16:9`	`1:121:94:33:416:99:16adaptive`
`duration` Clip duration.	`string`	Optional	`5`	`4–15 (seconds)`
`resolution` Output resolution. 1080p-plus and 4k are available on pro only.	`string`	Optional	`720p`	`720p1080p1080p-plus4k`
`image_url` Start frame — required for image-to-video.	`string (URL)`	Optional	`—`	`public https URL`
`end_image_url` Optional end frame.	`string (URL)`	Optional	`—`	`public https URL`
`media_urls` Required for media-to-video. Video URLs must support duration probing.	`string[] (URL)`	Optional	`—`	`≤ 12 public https image/video URLs`
`generate_audio` Generate an audio track.	`boolean`	Optional	`true`	`truefalse`
`fixed_lens` Lock the camera lens.	`boolean`	Optional	`false`	`truefalse`
`seed` Not supported on the real channel or mini tier.	`integer`	Optional	`—`	`-1 – 4294967295`

Seedance prompt guide

Seedance prompts work best as concrete director instructions. Describe the subject, action, scene, camera motion, visual style, and constraints, then map every reference asset to the right API parameter.

Use image_url for the opening frame, end_image_url for the closing frame, and media_urls for character, motion, style, source-video, or extension references.
Describe asset roles in natural language inside prompt. Do not send raw asset ids, asset:// URLs, or in-app-only labels such as @图片1.
For edits say “strictly edit the supplied source video”; for extensions say “continue from the supplied previous clip.”
For complex scenes, use ordered shots plus a style and constraint package: stable faces, natural motion, no deformation, no watermark, no logo, and no subtitles unless intended.

Request

bash

curl -X POST https://seedance2ai.io/api/v1/video/seedance2 \
  -H "Authorization: Bearer $SEEDANCE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: demo-video-001" \
  -d '{
    "mode": "text-to-video",
    "quality_tier": "standard",
    "prompt": "A cinematic shot of a glass train crossing a snowy mountain bridge",
    "aspect_ratio": "16:9",
    "duration": "5",
    "resolution": "720p"
  }'

Response202

json

{
  "id": "sd2_xxxxx",
  "status": "processing",
  "model": "seedance2",
  "quality_tier": "standard",
  "channel": "standard",
  "credits_used": 30
}

Check task status

GET

/api/v1/tasks/{id}

Request

bash

curl https://seedance2ai.io/api/v1/tasks/sd2_xxxxx \
  -H "Authorization: Bearer $SEEDANCE_API_KEY"

Response200

json

{
  "id": "sd2_xxxxx",
  "status": "completed",
  "model": "seedance2",
  "quality_tier": "standard",
  "channel": "standard",
  "credits_used": 30,
  "credits_refunded": 0,
  "output": {
    "video_url": "https://...",
    "last_frame_url": "https://...",
    "seed": 123
  },
  "error": null,
  "created_at": "2026-06-03T10:00:00.000Z",
  "updated_at": "2026-06-03T10:03:12.000Z"
}

status: processing · completed · failed

Error codes

All errors share this shape:

json

{ "error": { "code": "invalid_request", "message": "Invalid request body" } }

Code	HTTP	Meaning
`unauthorized`	`401`	Missing, invalid, or revoked API key.
`invalid_request`	`400`	Bad input or unsupported field.
`insufficient_credits`	`402`	Not enough credits on the balance.
`rate_limited`	`429`	Too many requests — limit is 30 requests per 60 seconds per account. Retry after the Retry-After response header (in seconds).
`idempotency_conflict`	`409`	Same Idempotency-Key reused with a different body, or still running.
`service_busy`	`503`	Temporary upstream or credit-concurrency issue. Retry.
`not_found`	`404`	Task does not exist or does not belong to this key owner.
`internal_error`	`500`	Unexpected server-side failure.

Use with Claude Code

Hit Copy for AI to grab the full API as clean Markdown, paste it into Claude Code or Codex, and let it wire up the integration. Or point the agent straight at the raw text endpoint.

Open llms.txt

Skill

Install the Seedance skill in Claude Code, Codex, or any agent — it writes cinematic prompts and renders them through the API for you.

bash

# Download the one-file skill from Seedance 2 AI
mkdir -p ~/.claude/skills/seedance
curl -L https://seedance2ai.io/downloads/seedance-skill.md -o ~/.claude/skills/seedance/SKILL.md

Download skill

FAQ

Who can use the API?

Anyone with credits. There is no plan gate — any account with credits can create a key and call the API.

How do I get credits?

Top up or subscribe on the pricing page. Credits are added to your balance instantly.

Are credits shared between the website and the API?

Yes — your personal credit balance powers both your web generation and your API calls. On a team, API calls use each member's own personal balance, not the shared team pool.

How do I start?

Create an API key in your dashboard, then call the endpoints with a Bearer token (see Quickstart above).

What if a call returns insufficient_credits?

Your balance is empty — top up on the pricing page and retry.