Wan 3.0 Video — video API
Use alibaba/wan3.0-video for Wan text-to-video, or image-to-video from a first frame, at 480p, 720p, or 1080p through the Quotaflow /openai/v1/videos task API: create a task, store the returned id, and poll until the task completes. It uses the same API as the other video models; compare them on the Videos page.
Wan, Kling, Seedance, and Veo are different video model families. alibaba/wan3.0-video is never used as a fallback for another family's model, and no other model stands in for it.
Model contract
| Property | Value |
|---|---|
| Model id | alibaba/wan3.0-video, as /models lists it (wan3.0-video is also accepted) |
| Endpoint | POST https://api.quotaflow.ai/openai/v1/videos |
| Status endpoint | GET https://api.quotaflow.ai/openai/v1/videos/{task_id} |
| Content endpoint | GET https://api.quotaflow.ai/openai/v1/videos/{task_id}/content |
durationSeconds | 2–30; default 5 |
resolution | 480p, 720p, or 1080p; default 1080p |
aspect_ratio | adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, or 21:9; default adaptive |
generate_audio | optional; when omitted, the model's default applies |
| Modes | text_to_video (the default), image_to_video (with first_frame_url) |
first_frame_url | Base64 data URL of the first frame; makes the task image_to_video |
Call /models with your production key before launch. Video access is key-enabled: the default all-model key has it. Only a key with access to the Wan video line lists alibaba/wan3.0-video.
Text-to-video example
curl https://api.quotaflow.ai/openai/v1/videos \
-H "Authorization: Bearer $QUOTAFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "alibaba/wan3.0-video",
"prompt": "A paper boat drifting across a still pond at sunrise, slow camera pan.",
"durationSeconds": 5,
"resolution": "1080p",
"aspect_ratio": "16:9",
"generate_audio": false,
"max_cost_usd": 2
}'
First-frame example
Send a first frame and the task is image_to_video (omit mode, or send image_to_video). Frames are Base64 data URLs; an https:// image link is refused, and Quotaflow hosts the frame for the model itself. aspect_ratio and generate_audio work as they do for text-to-video.
curl https://api.quotaflow.ai/openai/v1/videos \
-H "Authorization: Bearer $QUOTAFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "alibaba/wan3.0-video",
"mode": "image_to_video",
"prompt": "Keep the product shape and color consistent, slow camera push-in.",
"first_frame_url": "data:image/png;base64,iVBORw0KGgo...",
"durationSeconds": 5,
"resolution": "1080p",
"max_cost_usd": 2
}'
Poll the task
curl https://api.quotaflow.ai/openai/v1/videos/$TASK_ID \
-H "Authorization: Bearer $QUOTAFLOW_API_KEY"
Download the completed video
curl -L https://api.quotaflow.ai/openai/v1/videos/$TASK_ID/content \
-H "Authorization: Bearer $QUOTAFLOW_API_KEY" \
--output wan.mp4
The content endpoint redirects to the video file; add ?format=json to receive { "url", "expires_at" } instead.
Notes
- Send only the fields above plus
promptandmax_cost_usd. A last frame (last_frame_url), reference videos, reference images,quality,frame_rate,watermark: true,return_last_frame,callback_url, andexecution_expires_afterare refused with400, as is amodeother thantext_to_videoorimage_to_video, a frame ontext_to_video, andimage_to_videowithout a frame.watermark: false,frame_rate: 0, and an emptyquality,last_frame_url, orcallback_urlcount as omitted. - The request body is limited to 11 MB, frame included.
durationSeconds: -1is not accepted: send a length within 2–30 seconds, or omit it for 5.- If the selected key does not list
alibaba/wan3.0-videofrom/models, do not retry as a transient error; request Wan video access for that key.
Next steps
- Read the Videos endpoint guide.
- Check
/modelswith your production key for currently enabled video models. - Browse all supported models.