MCP / Models / Text to video

Wan 2.2 Text to Video MCP: open-weights video

Wan 2.2 Text to Video runs Alibaba's open Wan 2.2 model on FlyMy.AI GPUs: cinematic clips with fluid, realistic motion, billed by run time. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

Use Wan 2.2 Text to VideoInputs and price
No API key$5.97 / hrText to videoAlibabaCommercial use
Wan 2.2 Text to Video sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Wan 2.2 Text to Video in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/wan2-2-text-to-video.md. Help me connect the FlyMy.AI MCP to this assistant, then run Wan 2.2 Text to Video (flymyai/wan2-2-text-to-video) for this task: Make a video of a fox running through fresh snow at sunrise with Wan 2.2 Text to Video.
Open FlyMy.AIDownload brief

What Wan 2.2 Text to Video does

Control the clip with num_frames, fps, width and height (832x480 by default), num_inference_steps and the two guidance scales of Wan 2.2's mixture-of-experts design; negative_prompt lists what to avoid.

Wan 2.2 Text to Video inputs

Every input of flymyai/wan2-2-text-to-video as its live schema lists them. Returns output (array).

InputType, values and default
# prompt
string required
# negative_prompt
string optional
# num_frames
integer required Default: 81
# num_inference_steps
integer required Default: 40
# guidance_scale
number optional Default: 4.0
# fps
integer optional Default: 16
# guidance_scale_2
number optional Default: 3.0
# width
integer optional Default: 832
# height
integer optional Default: 480

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Make a video of a fox running through fresh snow at sunrise with Wan 2.2 Text to Video.”runs flymyai/wan2-2-text-to-video
“Write and render a short ad for a reusable water bottle with Wan 2.2 Text to Video: three quick shots ending on the product.”runs flymyai/wan2-2-text-to-video
“Generate a calm, slow-camera clip of a chef plating a dessert in slow motion with Wan 2.2 Text to Video.”runs flymyai/wan2-2-text-to-video

Wan 2.2 Text to Video price

$5.97 per hour of run time, billed per second. Billed per second of run time, $5.97 an hour. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

See usage pricing →

Call Wan 2.2 Text to Video from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

From an agent, through the MCP

The agent calls get_model_schema, then run_model with:

{
  "endpoint_id": "flymyai/wan2-2-text-to-video",
  "input": {
    "prompt": "Steam rises from a ceramic mug on a sunlit kitchen counter, slow camera push-in",
    "num_frames": "81",
    "num_inference_steps": "40"
  }
}

From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/wan2-2-text-to-video/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/wan2-2-text-to-video/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Steam rises from a ceramic mug on a sunlit kitchen counter, slow camera push-in' \
  -F 'num_frames=81' \
  -F 'num_inference_steps=40'

Questions about Wan 2.2 Text to Video

Do I need a Alibaba API key for Wan 2.2 Text to Video?

No. Wan 2.2 Text to Video runs on FlyMy.AI GPUs, so you need no Alibaba key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Wan 2.2 Text to Video cost?

$5.97 per hour of run time, billed per second. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

How do I use Wan 2.2 Text to Video in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Make a video of a fox running through fresh snow at sunrise with Wan 2.2 Text to Video." Your agent reads the inputs with get_model_schema and runs flymyai/wan2-2-text-to-video with run_model.

What does Wan 2.2 Text to Video need as input?

Wan 2.2 Text to Video requires prompt, num_frames and num_inference_steps; it also takes 6 optional inputs, each listed on this page with its allowed values and default.

Can I call Wan 2.2 Text to Video from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/wan2-2-text-to-video/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

Go to the source

Wan 2.2 Text to Video in the playground →Model endpoints in the docs →Text to video guide →Every model on FlyMy.AI →Every MCP in the catalog →Usage pricing →

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.