curl --request POST \
--url https://api.goenhance.ai/api/v1/videos/generations \
--header 'Authorization: <authorization>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "seedance-2-0",
"prompt": "A cat plays piano in moonlight, cinematic close-up",
"duration": 8,
"quality": "720p",
"aspect_ratio": "16:9",
"generate_audio": true
}
'{
"code": 0,
"msg": "Success",
"data": {
"img_uuid": "c12b656c-747a-44fd-9c80-add79b0c52d5",
"cost": 5.82
}
}Seedance 2.0 Mini Reference to Video
The most affordable tier of Seedance 2.0 reference-to-video. Drive generation with reference images, videos and audio — reference them inside the prompt as @image1, @video1, @audio1.
Pricing — per second of generated video, in tokens (USD at $0.02/token). Same as Seedance 2.0 Mini standard:
| resolution | tokens/s | USD/s |
|---|---|---|
| 480p | 2.99 | $0.060 |
| 720p | 6.44 | $0.129 |
Returns an img_uuid; poll GET /api/v1/jobs/detail (or use custom_callback_url) to get the generated video.
⚠️ When ref_videos is used, the input video counts toward the bill. The charge becomes (total input video seconds + output duration) × rate × 0.8 — the reference footage is billed at the same per-second rate as the output, with a 20% discount applied to the whole thing. Input length is measured from your files before any tokens are deducted, so a 6s reference video on a 5s generation is billed as 11 seconds × 0.8, not 5.
Requests with only ref_imgs (no ref_videos) are unaffected: output duration × rate.
curl --request POST \
--url https://api.goenhance.ai/api/v1/videos/generations \
--header 'Authorization: <authorization>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "seedance-2-0",
"prompt": "A cat plays piano in moonlight, cinematic close-up",
"duration": 8,
"quality": "720p",
"aspect_ratio": "16:9",
"generate_audio": true
}
'{
"code": 0,
"msg": "Success",
"data": {
"img_uuid": "c12b656c-747a-44fd-9c80-add79b0c52d5",
"cost": 5.82
}
}Headers
Body
Model name. Must be seedance-2-0-mini-refs.
seedance-2-0-mini-refs Text prompt. Chinese: recommended up to 500 characters; English: recommended up to 1000 words.
Reference images (up to 9). jpeg/png/webp, ≤30MB each, 300–6000px, aspect ratio 0.4–2.5. Referenced in the prompt as @image1, @image2…
9Reference videos for camera/motion reference or editing source (up to 3). mp4/mov, 2–15s each and ≤15s total, ≤50MB each. Referenced in the prompt as @video1…. ⚠️ Using this field changes how the request is priced — see the pricing note above.
3Reference audio for background music, effects or voice (up to 3). wav/mp3, 2–15s each and ≤15s total, ≤15MB each. Requires at least one ref_imgs or ref_videos item. Referenced in the prompt as @audio1…
3Any integer from 4 to 15 seconds.
4 <= x <= 15Output resolution. resolution is accepted as a compatible alias.
480p, 720p Output aspect ratio. Image-to-video defaults to adaptive. ratio is accepted as a compatible alias.
16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive Generate synchronized audio at no additional charge.
Optional public HTTPS callback URL. custom_callback_url is accepted as a compatible alias.