Seedance 2.5 video generation (async): omit image for text-to-video, include image (first frame by default) for image-to-video; duration is any integer 4-30 seconds, resolution 480P/720P, size 16:9/9:16/21:9/4:3/1:1/3:4, audio toggles the generated soundtrack (default true). Returns a job id (HTTP 202); poll GET /v1/videos/jobs/{id} until status=succeeded, result in data[0].url (a re-hosted mp4). Billed per second, fully refunded on failure.
Try in Playground →Authentication
Authorization: Bearer YOUR_API_KEY Content-Type: application/json
Create an API Key in the console to start.
Request body
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model ID, here seedance-2.5. |
| prompt | string | Yes | Text prompt describing the video, camera and motion. Max 5000 bytes (UTF-8; a Chinese character counts as 3). With multiple reference images you can address them as @Image1 / @Image2 in the prompt, e.g. "the character from @Image1 in the scene from @Image2"; without tokens the model decides on its own. |
| duration | integer | No | Length in seconds, any integer 4-30 (default 4); alias seconds. Billed per second. |
| resolution | string | No | Resolution: 480P / 720P. |
| size | string | No | Aspect ratio: 16:9 (default) / 9:16 / 21:9 / 4:3 / 1:1 / 3:4; alias aspect_ratio. |
| audio | boolean | No | Whether to generate an audio track, default true. |
| image | string | No | Image-to-video: include a reference image (used as the first frame by default) — a public URL, a data: URI, or base64; omit for text-to-video. |
| images | array | No | Multiple reference images, up to 30 for this model. Each item may be a public URL, a data: URI, or base64. Exceeding the cap is rejected, never truncated. Alias: reference_images. |
| image_role | string | No | How the reference images are used: first_frame (default; a second image becomes the last frame) or reference (subject/style references — use this for multiple images). Passing reference_images defaults to reference. |
| audio_reference | string / array | No | Public http(s) URL(s) for reference audio, up to 10. Must accompany a reference image or video; alias audio_references (do not send both). |
| video_references | array | No | Public http(s) URL(s) for source video, up to 10. Public links only (a data: URI fails upstream); cannot combine with a reference image or first/last frame. |
Request example
# 1) submit -> 202 {"id":"img_...","status":"queued"}
curl https://nezhagate.com/v1/videos/generations -H 'Authorization: Bearer YOUR_API_KEY' -H 'Content-Type: application/json' -d '{"model": "seedance-2.5", "prompt": "a cat surfing a wave at sunset", "duration": 4, "resolution": "720P", "size": "16:9"}'
# image-to-video: also pass "image": "https://example.com/first-frame.png"
# 2) poll every ~5s until status=succeeded, then read data[0].url
curl https://nezhagate.com/v1/videos/jobs/img_3f9a...c2 -H 'Authorization: Bearer YOUR_API_KEY'Response
{
"id": "img_3f9a...c2",
"object": "video.generation.job",
"status": "queued",
"model": "seedance-2.5"
}Async video job (submit → poll)
One model; params pick the type: tier=lite/fast/quality, resolution=720p/1080p/4k (1080p/4k need quality), size=16:9/9:16, duration=4s/6s/8s; add an image param for image-to-video (first frame). Returns HTTP 202 + a job id; poll until status=succeeded, result in data[0].url (a re-hosted mp4, ~1-2 min).
curl https://nezhagate.com/v1/videos/generations -H 'Authorization: Bearer YOUR_API_KEY' -H 'Content-Type: application/json' -d '{"model": "seedance-2.5", "prompt": "a cat surfing at sunset", "tier": "quality", "resolution": "1080p", "size": "16:9", "duration": "8s"}'{ "id": "img_3f9a...c2", "object": "video.generation.job", "status": "queued", "model": "seedance-2.5" }curl https://nezhagate.com/v1/videos/jobs/img_3f9a...c2 -H 'Authorization: Bearer YOUR_API_KEY'
{
"id": "img_3f9a...c2",
"object": "video.generation.job",
"status": "succeeded",
"model": "seedance-2.5",
"data": [{ "url": "https://img.nezhagate.com/i/9f86d081a8....mp4" }]
}Billed per second ($0.158/s x duration); the hold equals the settle exactly, and a failed or timed-out render is refunded in full automatically.
Error codes
| Code | Description |
|---|---|
| 401 | Invalid or missing API key |
| 402 | Insufficient balance / key limit reached |
| 400 | Invalid parameters or model |
| 429 | Rate limited |
| 502 | All upstream providers failed |
