MCP / Models / Reference video, editing and lip sync

Wan 3.0 Reference to Video MCP: images, clips and voices

Alibaba Wan 3.0 builds a video of up to 30 seconds from reference images, clips and audio, keeping characters, places, style and voice. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

Use Wan 3.0 Reference to VideoInputs and price
No API keyfrom $0.05 / sReference to videoAlibabaCommercial use
Wan 3.0 Reference to Video sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Wan 3.0 Reference 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/wan-3-0-ref2v.md. Help me connect the FlyMy.AI MCP to this assistant, then run Wan 3.0 Reference to Video (flymyai/wan-3_0-ref2v) for this task: Use Wan 3.0 Reference to Video to make a clip of the character in my reference images walking along a misty forest trail.
Open FlyMy.AIDownload brief

What Wan 3.0 Reference to Video does

Send up to 10 reference_images, 5 reference_videos and 5 reference_audios, and describe in the prompt who and what they are and how to use them. Choose resolution (480P, 720P or 1080P), ratio, duration (2 to 30 seconds or -1), audio and seed.

Wan 3.0 Reference to Video inputs

Every input of flymyai/wan-3_0-ref2v as its live schema lists them. Returns video (array).

InputType, values and default
# prompt
string required What happens and how the references are used
# reference_images
string optional Up to 10 image URLs (a JSON array or one URL)
# reference_videos
string optional Up to 5 mp4/mov URLs, 1-15 s each, 15 s in total
# reference_audios
string optional Up to 5 wav/mp3 URLs, 1-15 s each, 15 s in total
# resolution
string optional Allowed: 480P, 720P, 1080P Default: 720P Billed per generated second: $0.05 at 480P, $0.10 at 720P, $0.20 at 1080P
# ratio
string optional Allowed: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive Default: adaptive Aspect ratio; adaptive follows the input media
# duration
integer optional Allowed: -1 to 30 Default: 5 Length in seconds, 2-30; -1 lets the model choose (up to 30)
# audio
boolean optional Default: true Generate sound with the video
# prompt_extend
boolean optional Default: true Let the model expand the prompt with more detail
# watermark
boolean optional Default: false
# seed
integer optional Allowed: 0 to 2147483647 Fix for repeatable results
# enable_safety_checks
boolean optional Default: true Alibaba content inspection of the input and the video

Ask your agent

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

“Use Wan 3.0 Reference to Video to make a clip of the character in my reference images walking along a misty forest trail.”runs flymyai/wan-3_0-ref2v
“Keep my product from these three photos and show it on a picnic blanket in a sunny park with Wan 3.0 Reference to Video.”runs flymyai/wan-3_0-ref2v
“Make a short ad with Wan 3.0 Reference to Video where the person from my references unboxes an electric scooter.”runs flymyai/wan-3_0-ref2v

Wan 3.0 Reference to Video price

From $0.05 per second of duration, depending on resolution. A run at the default settings costs $0.50. A run costs $0.10 to $6.00, depending on resolution and duration. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

SettingPrice
resolution 480P$0.05 per second
resolution 720P$0.10 per second
resolution 1080P$0.20 per second

See usage pricing →

Call Wan 3.0 Reference 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/wan-3_0-ref2v",
  "input": {
    "prompt": "Keep the subject and its motion, set the scene on a beach at golden hour"
  }
}

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/wan-3_0-ref2v/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/wan-3_0-ref2v/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Keep the subject and its motion, set the scene on a beach at golden hour'

Questions about Wan 3.0 Reference to Video

Do I need a Alibaba API key for Wan 3.0 Reference to Video?

No. Wan 3.0 Reference to Video runs on FlyMy.AI's account, 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 3.0 Reference to Video cost?

From $0.05 per second of duration, depending on resolution. 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 3.0 Reference 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: "Use Wan 3.0 Reference to Video to make a clip of the character in my reference images walking along a misty forest trail." Your agent reads the inputs with get_model_schema and runs flymyai/wan-3_0-ref2v with run_model.

What does Wan 3.0 Reference to Video need as input?

Wan 3.0 Reference to Video requires prompt; it also takes 11 optional inputs, each listed on this page with its allowed values and default.

Can I call Wan 3.0 Reference to Video from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/wan-3_0-ref2v/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

Go to the source

Wan 3.0 Reference to Video in the playground →Wan 3.0 Reference to Video guide in the docs →Model endpoints in the docs →Reference video, editing and lip sync 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.