Seedance 2.0

Generate videos from text, frames, or multimodal references.

POST

/api/v1/generations

Example request

Set your FLUX_API_KEY before running. See the parameters below for supported settings.

cURL

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "seedance-2",
  "input": {
    "mode": "text-to-video",
    "prompt": "A calm seaside sunrise with gentle camera movement",
    "resolution": "480p",
    "duration": 4,
    "sound": false,
    "aspect_ratio": "16:9"
  }
}'

Parameters

Set model to seedance-2. These fields belong inside input.

Parameter	Description
`resolution` string · Optional	Output resolution tier. Values are case-sensitive. `480p720p1080p4k` Default: `480p`
`aspect_ratio` string · Optional	Output proportions; see mode constraints below. `auto1:13:44:39:1616:921:9` Default: `auto`
`sound` boolean · Optional	Generate sound with the video. This is not a reference audio input. Default: `true`
`mode` string · Required	Choose a supported generation mode. `text-to-videofirst_and_last_framesomni_reference`
`prompt` string · Required	Describe the desired output. Minimum 1 characters. Maximum 5,000 characters.
`image_urls` string[] · Optional	Public HTTPS reference images. Video image order and count depend on mode. Up to 9 items.
`video_urls` string[] · Optional	Public HTTPS MP4 or MOV references. Flux measures duration before charging. Maximum file size 200 MiB. Up to 3 items.
`audio_urls` string[] · Optional	Public HTTPS MP3, WAV or M4A references. Flux measures duration before charging. Maximum file size 15 MiB. Audio is not billed separately. Up to 3 items.
`duration` integer · Optional	Output duration in seconds. See model constraints for editing and automatic duration. Range: 4–15. Default: `5`
`web_search` boolean · Optional	Allow web search context. Default: `false`

Reference media

Use your own publicly accessible HTTPS media URLs. Links must remain valid throughout queueing and generation. Base64 and file upload bodies are not supported by this endpoint.

first_and_last_frames

cURL

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "seedance-2",
  "input": {
    "mode": "first_and_last_frames",
    "prompt": "A calm seaside sunrise with gentle camera movement",
    "resolution": "480p",
    "duration": 4,
    "sound": false,
    "aspect_ratio": "auto",
    "image_urls": [
      "https://example.com/front.jpg",
      "https://example.com/back.jpg"
    ]
  }
}'

omni_reference

cURL

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "seedance-2",
  "input": {
    "mode": "omni_reference",
    "prompt": "A calm seaside sunrise with gentle camera movement",
    "resolution": "480p",
    "duration": 4,
    "sound": false,
    "aspect_ratio": "auto",
    "image_urls": [
      "https://example.com/front.jpg",
      "https://example.com/back.jpg"
    ]
  }
}'

Video and audio references

cURL

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "seedance-2",
  "input": {
    "mode": "omni_reference",
    "prompt": "A calm seaside sunrise with gentle camera movement",
    "resolution": "480p",
    "duration": 4,
    "sound": false,
    "aspect_ratio": "auto",
    "image_urls": [
      "https://example.com/front.jpg"
    ],
    "video_urls": [
      "https://example.com/reference.mp4"
    ],
    "audio_urls": [
      "https://example.com/reference.mp3"
    ]
  }
}'

Credits

Resolution	Without video / second	With video / second
480p	10	6.142857
720p	21.428571	13.285714
1080p	52.857143	32.714286
4k	111.428571	66.714286

Video reference seconds are included in the billable duration. See the model-specific rounding and editing rules below. Sound does not change the price. Confirmed failed requests are refunded.

Credits = ceil((output seconds + measured input video seconds) × rate), using the exact website pricing rate. Displayed rates are rounded to 6 decimal places. Audio is not billed separately.

Constraints

Output duration is fixed at 4–15 seconds. First/last frames accept 1–2 images with aspect_ratio auto.

Omni reference supports up to 9 images, 3 videos and 3 audio files. Each video/audio must be 2–15 seconds; video total and audio total must each be at most 15 seconds.

Use returned dimensions when available. Unverified video dimensions are null. Videos are delivered as MP4. Reference and editing rules depend on the model.

Response

A successful submission returns HTTP 202 and a request ID. Response excerpt:

JSON

{
  "id": "REQUEST_ID",
  "model": "seedance-2",
  "status": "processing"
}

Continue readingPoll & download