# Wan 3.0 Video Extend MCP and API by Alibaba | FlyMy.AI

> Alibaba Wan 3.0 Video Extend continues a clip forward or backward, up to 30 seconds in all, keeping its characters, motion, camera and sound.

Page: https://flymy.ai/mcp/models/wan-3-0-video-extend/

MCP / Models / Reference video, editing and lip sync

# Wan 3.0 Video Extend MCP: continue a clip up to 30 seconds

Alibaba Wan 3.0 Video Extend continues a clip forward or backward, up to 30 seconds in all, keeping its characters, motion, camera and sound. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Wan 3.0 Video Extend](https://flymy.ai/mcp/models/wan-3-0-video-extend/#start) [Inputs and price](https://flymy.ai/mcp/models/wan-3-0-video-extend/#inputs)

No API key, from $0.05 / s, Video extension, Alibaba, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Wan 3.0 Video Extend 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-video-extend.md. Help me connect the FlyMy.AI MCP to this assistant, then run Wan 3.0 Video Extend (flymyai/wan-3_0-video-extend) for this task: Continue my clip with Wan 3.0 Video Extend: the camera pans to the mountains.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/wan-3-0-video-extend.md)

## What Wan 3.0 Video Extend does

Send video (MP4 or MOV, 1 to 15 seconds, up to 100 MB) and a prompt that says what happens in the new part, for example 'The camera pans to the mountains'. direction is forward, the default, to carry the clip on, or backward to make what led up to it; the result is your clip with the new seconds after or before it. duration is the length of the whole result, up to 30 seconds, and -1 lets the model choose. Add reference_images or reference_audios, and choose resolution (480P, 720P or 1080P). Billing counts the seconds of the clip you send as well as the seconds you get. It does not edit what is already in the clip, which Wan 3.0 Video Edit does.

## Wan 3.0 Video Extend inputs

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

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-prompt) `prompt` | string required What to do with the video |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-video) `video` | file required Allowed: video file, as a URL or upload The video: MP4 or MOV, 1-15 s, at least 16 fps, 240-4096 px per side, up to 100 MB; a link or an upload |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-direction) `direction` | string optional Allowed: forward, backward Default: `forward` Continue after the video, or make what came before it |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-duration) `duration` | integer optional Allowed: -1 to 30 Default: `-1` Length of the whole result in seconds (the clip plus the new part), 2-30; -1 lets the model choose |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-resolution) `resolution` | string optional Allowed: 480P, 720P, 1080P Default: `720P` Billed per second of video at the resolution's rate, for the clip you give plus the clip you get: $0.05 at 480P, $0.10 at 720P, $0.20 at 1080P |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-reference_images) `reference_images` | string optional Up to 10 image links (a JSON array or one link); the prompt calls them "Image 1", "Image 2" |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-reference_audios) `reference_audios` | string optional Up to 5 WAV or MP3 links, 1-15 s each and 15 s in all (a JSON array or one link) |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-ratio) `ratio` | string optional Allowed: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive Default: `adaptive` Aspect ratio; adaptive follows the video you give |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-audio) `audio` | boolean optional Default: `true` Sound in the result; switching it off does not change the price |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-prompt_extend) `prompt_extend` | boolean optional Default: `true` Let the model expand the prompt with more detail |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-watermark) `watermark` | boolean optional Default: `false` |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-seed) `seed` | integer optional Allowed: 0 to 2147483647 Fix for repeatable results |
| [#](https://flymy.ai/mcp/models/wan-3-0-video-extend/#input-enable_safety_checks) `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.

**“Continue my clip with Wan 3.0 Video Extend: the camera pans to the mountains.”** runs `flymyai/wan-3_0-video-extend`

**“Extend my product video with Wan 3.0 Video Extend so it ends on a close-up of the logo.”** runs `flymyai/wan-3_0-video-extend`

**“Add a few seconds to the end of my clip with Wan 3.0 Video Extend: the dog runs out of frame.”** runs `flymyai/wan-3_0-video-extend`

## Wan 3.0 Video Extend price

From $0.05 per second of video, depending on resolution; the clip you give counts as well as the clip you get (30 s in all). A run costs $0.15 to $6.00, depending on resolution and video. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

| Setting | Price |
|---|---|
| resolution 480P | $0.05 per second |
| resolution 720P | $0.10 per second |
| resolution 1080P | $0.20 per second |

[See usage pricing →](https://flymy.ai/pricing/)

## Call Wan 3.0 Video Extend 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-video-extend",
  "input": {
    "prompt": "Keep the subject and its motion, set the scene on a beach at golden hour",
    "video": "https://example.com/clip.mp4"
  }
}
```

### 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-video-extend/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/wan-3_0-video-extend/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' \
  -F "video=@clip.mp4"
```

## Questions about Wan 3.0 Video Extend

**Do I need an Alibaba API key for Wan 3.0 Video Extend?**

No. Wan 3.0 Video Extend 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 Video Extend cost?**

From $0.05 per second of video, depending on resolution; the clip you give counts as well as the clip you get (30 s in all). There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use Wan 3.0 Video Extend in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Continue my clip with Wan 3.0 Video Extend: the camera pans to the mountains." Your agent reads the inputs with get_model_schema and runs flymyai/wan-3_0-video-extend with run_model.

**What does Wan 3.0 Video Extend need as input?**

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

**Can I call Wan 3.0 Video Extend from my own code?**

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

## More reference video, editing and lip sync models

Keep characters and products from references, edit, extend, reframe or upscale a clip, dub it into another language, sync lips to a voice, make a photo talk or time a video to your audio.

### Wan 3.0 Video Edit

Alibaba's Wan 3.0 changing a real clip by instruction, with reference images and audio.

Video editing / from $0.05 / s

Link: https://flymy.ai/mcp/models/wan-3-0-video-edit/

### Wan 3.0 Reference to Video

Wan 3.0 from references: the same cast, location and voice across 30 seconds.

Reference to video / from $0.05 / s

Link: https://flymy.ai/mcp/models/wan-3-0-ref2v/

### Wan 2.7 Video Edit

Wan 2.7 restyling a real clip, with up to four reference images.

Video editing / from $0.20 / s

Link: https://flymy.ai/mcp/models/wan-2-7-video-edit/

### Wan 2.7 Reference to Video

Wan 2.7 for keeping a character or style steady across a short clip.

Reference to video / from $0.10 / s

Link: https://flymy.ai/mcp/models/wan-2-7-ref2v/

### ByteDance Video Upscaler

Target-resolution upscaling to 8K with presets for AI clips, user video and old film.

Video upscaling / from $0.0072 / s

Link: https://flymy.ai/mcp/models/bytedance-video-upscaler/

### FLUX 3 Video Extend

FLUX 3 Video that picks up where your clip ends and carries on its motion, camera and scene.

Video extension / from $0.21 / s

Link: https://flymy.ai/mcp/models/flux-3-video-v2v/

## Go to the source

[Wan 3.0 Video Extend in the playground →](https://app.flymy.ai/models/flymyai/wan-3_0-video-extend), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Reference video, editing and lip sync guide →](https://docs.flymy.ai/guides/generate-videos), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.
