KinoGenie
Start for free
All toolsWan 2.2 API

Wan 2.2 API: Apache-2.0 Text to Video

Call Wan 2.2 TI2V 5B over a hosted API: a prompt in, a 4 to 15 second 1280x704 MP4 out, no soundtrack, billed per second of video. Run the preset directly on this page or call the same agent-ready endpoint from your product.

Run this tool View API recipe
LIVE TOOL
Run wan 2 2 5b
Drop a video, adjust the defaults if you need to, and download the result here.

or ·

Already have an account? Sign in

BEFORE / AFTER

See what the tool changes.

A real example: the after side is the unedited output of a KinoGenie job. Run the live form above to generate the same result from your own media.

BeforeSource video
WebM · VP9
mountain.webm
AfterCompatible MP4
Ready
MP4 · H.264
mountain.mp4

Demo footage: public-domain timelapses (Bureau of Land Management, Oregon · NASA SVS). Processed by the same pipeline the API and MCP tools call.

Useful defaults, typed options.

The tool slug stays stable while your agent supplies named media inputs and a narrow set of documented options.

  • Apache-2.0 weights, no clause on what you generate
  • 2.5 credits a second, the cheapest video we run
  • Same API and MCP server as the rest of the catalog
What this preset does
  1. 01Send a prompt to the hosted Wan 2.2 TI2V 5B endpoint
  2. 02Render 1280x704 on a GPU worker
  3. 03Tag the output as AI-generated (EU AI Act art. 50)
  4. 04Return a playable MP4 with a download URL
Stable endpointPOST /api/v1/tools/wan-2-2-5b
Live API request
{
  "inputs": [],
  "options": { "model": "wan-2-2-5b", "prompt": "A neon-lit ramen stall in the rain at night, steam rising off the bowl, slow push in.", "seconds": 5 }
}
Successful output example
{
  "result": {
    "output": {
      "filename": "wan-2-2-5b-output.mp4",
      "contentType": "video/mp4",
      "byteSize": 437021,
      "downloadUrl": "https://cdn.kinopipe.com/…"
    }
  }
}

Know the boundaries before you run.

No soundtrack. Wan 2.2 renders picture only, so a clip that needs sound wants MiniMax H3 or a separate audio pass
16:9 only, at 768p, which comes out 1280x704. A request for another ratio or resolution is refused with the reason rather than quietly reframed
No image-to-video yet. The graph supports it, our fleet has not measured it, so it is not offered
2.5 credits per second of video, so a 5 second clip is 13 credits, reserved when the job is queued and refunded if it fails
Rendering takes a few minutes, and longer when no worker is already warm. Poll the job or register a webhook

About wan 2.2 api

What is Wan 2.2 TI2V 5B?

An open-weight text-to-video model from Alibaba, released under Apache-2.0. The 5B is the size that runs on one GPU, which is why it is the one we host and why it costs what it costs.

Why is there no sound?

The model does not generate any. That is the trade against MiniMax H3, which renders picture and stereo audio in the same pass. If the clip needs sound, use H3, or add music to a Wan clip afterwards with add-music-to-video.

How much does a Wan 2.2 clip cost here?

2.5 credits per second, so a 5 second clip is 13 credits against 30 for the same length on MiniMax H3. On fal the same model is $0.15 flat for a clip of up to 5 seconds, which puts us between 1.28 and 2.91 times cheaper depending on your plan. Checked on their page on 2026-08-28.

Which licence applies to what I generate?

Apache-2.0, and it is the cleanest of anything we serve: one licence file, no territorial carve-out, and Alibaba claims no rights over the output. Compare that with FLUX.2 [dev], which forbids production use without a paid agreement, or HunyuanImage 3.0, whose licence grants nothing at all in the European Union.

Is this the newest Wan?

It is the newest one with open weights. Wan 2.5, 2.6, 2.7 and 3.0 are API-only, whatever a reseller may imply, so 2.2 is the last version of the line anyone can self-host. Watch the letters too: fal also sells Wan 2.2 A14B at $0.08 a second, and a price quoted for "Wan 2.2" without saying 5B or A14B is already wrong by a factor of 2.7.

How do I pick the model from an agent?

Call generate_video with model set to wan-2-2-5b, or call this page's own tool, which pins the model for you. Leave model out and you get MiniMax H3, which is the default.

Related media tools

MiniMax H3 API: Text to Video with Native Audio

Call the open-weight MiniMax H3 model over a hosted API: a prompt or a start frame in, a 4 to 15 second MP4 with synchronised stereo audio out, billed per second of video.

Explore

Generate AI Video from Text with an API

Turn a text prompt, or an image to animate, into a short video clip with native stereo audio, delivered as an MP4.

Explore