← All models
// video model

Wan 3.0 Video

video Budget
from20credits
// api

The Wan 3.0 Video API — in one request

Call the Wan 3.0 Video API through your SamAutomation key — submit a job with the model_id, then poll until it's done. One key for every model, no per-vendor onboarding or separate billing.

# 1. submit a generation job
POST /api/ai/jobs
{
  "model_id": "wan-3-0-video",
  "prompt": "the person in the photo turns and smiles",
  "image_urls": ["https://example.com/first-frame.jpg"],
  "options": { "aspect_ratio": "16:9", "resolution": "480p", "duration_s": 2 }
}
# → { "success": true, "job_id": 123, "status": "queued", "credits_charged": … }

# 2. poll until the video is ready
GET /api/ai/jobs/{job_id}
# → { "job_id": 123, "status": "success", "result_urls": ["…"] }
// questions

Wan 3.0 Video: the questions people ask

Does Wan 3.0 Video have an API?

Yes. On SamAutomation Wan 3.0 Video runs through one endpoint - POST /api/ai/jobs with model_id "wan-3-0-video" - so you do not need a separate account or key with the model maker. You submit a job and poll it until the video is ready.

How much does Wan 3.0 Video cost?

Wan 3.0 Video starts at 20 credits per job at its cheapest settings. Longer clips and higher resolution cost more. Credits come with a plan, and the same key also covers JSON-to-video rendering and every other model.

Is Wan 3.0 Video free?

No. Every render costs credits - 20 at the floor for Wan 3.0 Video. Plans bundle monthly credits.

Is Wan 3.0 Video restricted or region-locked?

You reach Wan 3.0 Video through this API with your SamAutomation key, not through the model maker's own app, so that app's sign-up and regional availability are not what gates you. The model's own content rules still apply to what you generate.

Where is the official Wan 3.0 Video site?

the model maker publishes the model itself; this page is about calling it as an API alongside every other model on one key, which is a different job from their consumer app.

Where is the Wan 3.0 Video API documentation, and is there a download?

There is nothing to download. The Wan 3.0 Video API documentation you need here is our own reference: one endpoint, one key, and the model_id above. the model maker publishes its own docs for the model, but those describe their platform, not this one.

Is Wan 3.0 Video available right now?

If it is listed on this page it is active on the platform and you can call it today. Model availability moves — makers retire versions and add tiers — so the list here is the current state rather than a promise about next quarter.

Is there a Wan 3.0 Video SDK, GitHub repo or Python example?

You do not need a vendor SDK here. Wan 3.0 Video is an HTTP call: POST /api/ai/jobs with your key and model_id "wan-3-0-video", then poll the job. Any language that can send JSON can drive it, and the request shape is the same for every model on this platform.

Is Wan 3.0 Video safe to use, and what happens to my input?

The practical questions are the same for every generation service: what the provider may do with what you upload, how long it is kept, and whether it can be used for training. Read that clause before you send client material through any model, ours included. the model maker publishes its own terms for the model itself.

Are the Wan 3.0 Video weights open source or on Hugging Face?

That is up to the model maker, not to us, and it differs per model and per release. If open weights matter to you, check the maker's own licence. Running it here is renting inference, not getting the weights.

Do I need the Wan 3.0 Video app to use it?

No. The consumer app and the API are separate products with separate limits. Here you call Wan 3.0 Video through this platform, so there is no app to install and no second subscription.

Generate with Wan 3.0 Video today

One key for JSON-to-video and every AI model — Wan 3.0 Video starts at 20 credits. Documented and ready for your pipeline.