Seedance 2.5 Flash via Dawnwood Models: $0.167/s at 720p and $0.078/s at 480p, on the same key and wallet as every other Seedance model.
In shortThe faster, lower-priced Seedance 2.5 tier: the same 30-second clips and request shape as 2.5, about 1.8× faster and priced like Seedance 2.0. Up to 10 reference images and 5 reference audios, 480p/720p. Call it as "model": "seedance-2.5-flash" on https://models.dawnwood.ai/v1/video/generations; you pay per requested second, only when the generation succeeds.
| Resolution | USD / s | 5 s clip | credits / s |
|---|---|---|---|
| 480p | $0.078 | $0.39 | 0.78 |
| 720p | $0.167 | $0.835 | 1.67 |
Compared: BytePlus ModelArk bills Seedance 2.5 Flash directly at $7 per million output tokens, about $0.152/s at 720p by our measurement of roughly 21,700 tokens per output second; buying direct needs a BytePlus account and is billed in tokens. More providers: Seedance API pricing compared.
| Field | Accepted values |
|---|---|
model | seedance-2.5-flash (the official dreamina-seedance-… id is accepted too) |
duration | Whole seconds, 4–30 |
resolution | 480p / 720p (no 1080p yet) |
ratio | 16:9 9:16 1:1 4:3 3:4 21:9 adaptive |
content[] text | At most one text item (the prompt) |
content[] images | Up to 10 image_url items, role first_frame, last_frame or reference_image (frames and reference images are not mixed in one task) |
content[] audio | Up to 5 audio_url items, role reference_audio |
content[] video | Not supported yet: video_url returns 400 unsupported_content |
generate_audio | true / false |
seed | Optional integer |
# 1. create a task
curl -s https://models.dawnwood.ai/v1/video/generations \
-H "Authorization: Bearer $DAWNWOOD_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: shot-0001" \
-d '{
"model": "seedance-2.5-flash",
"content": [
{"type": "text", "text": "A woman in a red coat turns at the top of a rain-soaked stairwell, slow push-in"},
{"type": "image_url", "image_url": {"url": "https://example.com/lead.png"}, "role": "reference_image"}
],
"resolution": "720p", "ratio": "9:16", "duration": 5, "generate_audio": true
}'
# -> {"id": "cgt-dw-..."}
# 2. poll until status is succeeded / failed / cancelled
curl -s https://models.dawnwood.ai/v1/video/generations/cgt-dw-... \
-H "Authorization: Bearer $DAWNWOOD_API_KEY"
Polling, errors, billing fields and the ModelArk alias path are in the API reference. Only successful generations are charged. New accounts get 30 free trial credits; after that the API spends purchased credits.
The same token can drive Dawnwood's production pipeline — bible, scripts, consistent cast and sets, rendering with QC — over its API or MCP.