The fullest ByteDance Seedance 2.0 channel (Chenyu). Text / image (first · first+last) / multimodal reference (up to 9 images + video + audio + native audio). The only channel that accepts REAL faces directly (filed account) — no asset library needed. Standard 480p/720p/1080p; Fast is faster & cheaper (480p/720p).
Near-identical names, different upstreams & capabilities. You are viewing the highlighted row.
| Model | Channel | Real person | Price |
|---|---|---|---|
| Seedance 2.0 ← | Chenyu · real-person multimodal | Real faces directly | $0.11–$0.33/s |
| Seedance 2.0 Official | Volcengine Ark direct | Via asset:// library | token-settled |
| Seedance 2.0 (sd-A) | Custom-A · Topaz HD | Via asset:// library | $0.073–$0.365/s |
| Seedance 2.0 Lite | Low-cost / anime | Own portrait library | $0.04–$0.15/s |
| Seedance 2.0 Cinematic | RunningHub film-grade | — | $1 / $2 / $3 |
Authorization: Bearer YOUR_API_KEY| Field | Required | Type | Description |
|---|---|---|---|
| Model | API name | Resolution | $/s |
| Seedance 2.0 | seedance-2.0 | 480p / 720p / 1080p | $0.13 / $0.26 / $0.33 |
| Seedance 2.0 Fast | seedance-2.0-fast | 480p / 720p | $0.11 / $0.22 |
Billed = $/s × duration (4-15s) — charged only on success, refunded on failure.
/api/v1/video/generations# Text-to-video (model: seedance-2.0 / seedance-2.0-fast)
curl -X POST https://apimodels.app/api/v1/video/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0",
"prompt": "a hummingbird hovering near a bright flower, slow motion",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5
}'
# Real-person / multimodal — this channel accepts REAL faces directly (no asset://):
# "images": ["https://.../face.jpg", ...(≤9)], "real_person": true
# Image-to-video: "first_frame_url" (+ "last_frame_url" for first+last)
# Reference video/audio: "videos": [...], "audios": [...]
# Poll for the result
curl "https://apimodels.app/api/v1/video/generations?task_id=TASK_ID" -H "Authorization: Bearer YOUR_API_KEY"| Field | Required | Type | Description |
|---|---|---|---|
| Field | Type | Description | |
| model | string | "seedance-2.0" / "seedance-2.0-fast" | |
| prompt | string | Prompt (optional with references), ≥3 chars | |
| resolution | string | 480p / 720p / 1080p (fast: 480p/720p) | |
| aspect_ratio | string | adaptive / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 | |
| duration | number | 4-15s, default 5 | |
| images | string[] | Multimodal reference images, up to 9 (incl. real people) | |
| real_person | boolean | Set true when references contain real people (moderation) | |
| first_frame_url / last_frame_url | string | First / last frame for image-to-video | |
| videos / audios | string[] | Reference video / audio |
Try it in the Playground
Yes — this channel accepts real faces directly (no asset library needed). Pass them as images[] with real_person: true. It is the only Seedance channel that takes raw real faces.
Per second by resolution: standard $0.13 / $0.26 / $0.33 for 480p / 720p / 1080p; Fast $0.11 / $0.22. Billed on duration (4–15s), charged only on success.