# Wan 2.1 First and Last Frame MCP and API by Alibaba | FlyMy.AI

> Wan 2.1 First and Last Frame makes a video that moves smoothly from your start image to your end image, on FlyMy.AI GPUs, billed by run time.

Page: https://flymy.ai/mcp/models/wan21-flf2v-fast/

MCP / Models / Image to video

# Wan 2.1 First and Last Frame MCP: bridge two images

Wan 2.1 First and Last Frame makes a video that moves smoothly from your start image to your end image, on FlyMy.AI GPUs, 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 2.1 First and Last Frame](https://flymy.ai/mcp/models/wan21-flf2v-fast/#start) [Inputs and price](https://flymy.ai/mcp/models/wan21-flf2v-fast/#inputs)

No API key, $3.00 / hr, First and last frame to video, Alibaba, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Wan 2.1 First and Last Frame 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/wan21-flf2v-fast.md. Help me connect the FlyMy.AI MCP to this assistant, then run Wan 2.1 First and Last Frame (flymyai/wan21-flf2v-fast) for this task: Animate the photo I attach with Wan 2.1 First and Last Frame: city lights come on as dusk falls.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/wan21-flf2v-fast.md)

## What Wan 2.1 First and Last Frame does

Send start_image and last_image with a prompt for the motion between them. Set num_frames and frames_per_second, resolution, aspect_ratio, steps, guide_scale and shift; enable_prompt_expansion expands a short prompt and negative_prompt lists what to avoid.

## Wan 2.1 First and Last Frame inputs

Every input of `flymyai/wan21-flf2v-fast` as its live schema lists them. Returns `output` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-prompt) `prompt` | string required Default: `Cars racing in slow motion` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-start_image) `start_image` | file required Allowed: image file, as a URL or upload |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-last_image) `last_image` | file required Allowed: image file, as a URL or upload |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-negative_prompt) `negative_prompt` | string optional |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-num_frames) `num_frames` | integer optional Default: `81` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-frames_per_second) `frames_per_second` | integer optional Default: `16` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-seed) `seed` | integer optional Default: `42` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-resolution) `resolution` | string optional Default: `720p` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-num_inference_steps) `num_inference_steps` | integer optional Default: `30` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-guide_scale) `guide_scale` | number optional Default: `5.0` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-shift) `shift` | number optional Default: `5.0` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-enable_safety_checker) `enable_safety_checker` | boolean optional Default: `true` |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-enable_prompt_expansion) `enable_prompt_expansion` | boolean optional |
| [#](https://flymy.ai/mcp/models/wan21-flf2v-fast/#input-aspect_ratio) `aspect_ratio` | string optional Default: `auto` |

## Ask your agent

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

**“Animate the photo I attach with Wan 2.1 First and Last Frame: city lights come on as dusk falls.”** runs `flymyai/wan21-flf2v-fast`

**“Turn my product shot into a clip with Wan 2.1 First and Last Frame, the camera slowly circling it.”** runs `flymyai/wan21-flf2v-fast`

**“Make a video with Wan 2.1 First and Last Frame that moves from my first picture to my second one with a smooth camera move.”** runs `flymyai/wan21-flf2v-fast`

## Wan 2.1 First and Last Frame price

$3.00 per hour of run time, billed per second. Billed per second of run time, $3.00 an hour. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

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

## Call Wan 2.1 First and Last Frame 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/wan21-flf2v-fast",
  "input": {
    "prompt": "Slow camera push-in with gentle, natural motion in the scene",
    "start_image": "https://example.com/photo.jpg",
    "last_image": "https://example.com/photo.jpg"
  }
}
```

### 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/wan21-flf2v-fast/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/wan21-flf2v-fast/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Slow camera push-in with gentle, natural motion in the scene' \
  -F "start_image=@photo.jpg" \
  -F "last_image=@photo.jpg"
```

## Questions about Wan 2.1 First and Last Frame

**Do I need a Alibaba API key for Wan 2.1 First and Last Frame?**

No. Wan 2.1 First and Last Frame 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 2.1 First and Last Frame cost?**

$3.00 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 2.1 First and Last Frame in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Animate the photo I attach with Wan 2.1 First and Last Frame: city lights come on as dusk falls." Your agent reads the inputs with get_model_schema and runs flymyai/wan21-flf2v-fast with run_model.

**What does Wan 2.1 First and Last Frame need as input?**

Wan 2.1 First and Last Frame requires prompt, start_image and last_image; it also takes 11 optional inputs, each listed on this page with its allowed values and default.

**Can I call Wan 2.1 First and Last Frame from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/wan21-flf2v-fast/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More image to video models

Animate a photo, or move from a first frame to a last one.

### Wan 3.0 Image to Video

Wan 3.0 from your image: up to 30 seconds, adaptive framing and a soundtrack.

Image to video / from $0.05 / s

Link: https://flymy.ai/mcp/models/wan-3-0-i2v/

### Wan 2.7 Image to Video

Wan 2.7 from a still: first-to-last-frame moves with natural motion.

Image to video / from $0.10 / s

Link: https://flymy.ai/mcp/models/wan-2-7-i2v/

### Wan 2.6 Image to Video

The previous Wan generation for animating a still at 720P or 1080P.

Image to video / from $0.10 / s

Link: https://flymy.ai/mcp/models/wan-2-6-i2v/

### Wan 2.2 Fast Image to Video

Wan 2.2 A14B animating your image with LoRA effects such as an orbit shot.

Image to video / from $0.135 / run

Link: https://flymy.ai/mcp/models/wan22-i2v-fast/

### Gemini Omni 1.2 Flash Image to Video

Gemini Omni from a photo: native sound, first-to-last-frame moves, up to 4K.

Image to video / from $0.024 / s

Link: https://flymy.ai/mcp/models/gemini-omni-1-2-flash-i2v/

### Seedance 2.5 Image to Video

Seedance 2.5 from a photo: up to 30 seconds, first-to-last-frame moves, real people allowed.

Image to video / from $0.10794 / s

Link: https://flymy.ai/mcp/models/bytedance-seedance-2-5-image-to-video/

## Go to the source

[Wan 2.1 First and Last Frame in the playground →](https://app.flymy.ai/models/flymyai/wan21-flf2v-fast), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Image to video 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 2026-11-09: 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.