# Kandinsky Video MCP and API - Text to video by Sber AI | FlyMy.AI

> Kandinsky Video generates a short clip from a text prompt with Sber AI's Kandinsky video model, with control over frames, size and guidance.

Page: https://flymy.ai/mcp/models/kandinsky-video/

MCP / Models / Text to video

# Kandinsky Video MCP: short clips from text with no API key

Kandinsky Video generates a short clip from a text prompt with Sber AI's Kandinsky video model, with control over frames, size and guidance. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Kandinsky Video](https://flymy.ai/mcp/models/kandinsky-video/#start) [Inputs and price](https://flymy.ai/mcp/models/kandinsky-video/#inputs)

No API key, $0.39 / run, Text to video, Sber AI, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Kandinsky 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/kandinsky-video.md. Help me connect the FlyMy.AI MCP to this assistant, then run Kandinsky Video (flymyai/kandinsky-video) for this task: Make a video of a skateboarder carving through an empty pool with Kandinsky Video.
```

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

## What Kandinsky Video does

Write the scene in the prompt and list what to avoid in negative_prompt. Choose num_frames (81 to 121), width and height (256 to 1024), num_inference_steps (8 to 50) and guidance_scale (1 to 10). It is priced per run.

## Kandinsky Video inputs

Every input of `flymyai/kandinsky-video` as its live schema lists them. Returns `output` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/kandinsky-video/#input-prompt) `prompt` | string required Default: `red car` |
| [#](https://flymy.ai/mcp/models/kandinsky-video/#input-negative_prompt) `negative_prompt` | string optional |
| [#](https://flymy.ai/mcp/models/kandinsky-video/#input-guidance_scale) `guidance_scale` | number optional Allowed: 1.0 to 10.0 Default: `1.0` |
| [#](https://flymy.ai/mcp/models/kandinsky-video/#input-num_inference_steps) `num_inference_steps` | integer optional Allowed: 8 to 50 Default: `16` |
| [#](https://flymy.ai/mcp/models/kandinsky-video/#input-num_frames) `num_frames` | integer optional Allowed: 81 to 121 Default: `81` |
| [#](https://flymy.ai/mcp/models/kandinsky-video/#input-width) `width` | integer optional Allowed: 256 to 1024 Default: `512` |
| [#](https://flymy.ai/mcp/models/kandinsky-video/#input-height) `height` | integer optional Allowed: 256 to 1024 Default: `512` |

## Ask your agent

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

**“Make a video of a skateboarder carving through an empty pool with Kandinsky Video.”** runs `flymyai/kandinsky-video`

**“Write and render a short ad for a plant-based protein bar with Kandinsky Video: three quick shots ending on the product.”** runs `flymyai/kandinsky-video`

**“Generate a calm, slow-camera clip of a barista pouring latte art in a busy cafe with Kandinsky Video.”** runs `flymyai/kandinsky-video`

## Kandinsky Video price

$0.39 per run. A run at the default settings costs $0.39. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

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

## Call Kandinsky 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/kandinsky-video",
  "input": {
    "prompt": "Steam rises from a ceramic mug on a sunlit kitchen counter, slow camera push-in"
  }
}
```

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

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/kandinsky-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'
```

## Questions about Kandinsky Video

**Do I need a Sber AI API key for Kandinsky Video?**

No. Kandinsky Video runs on FlyMy.AI's account, so you need no Sber AI key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Kandinsky Video cost?**

$0.39 per run. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

**How do I use Kandinsky 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 skateboarder carving through an empty pool with Kandinsky Video." Your agent reads the inputs with get_model_schema and runs flymyai/kandinsky-video with run_model.

**What does Kandinsky Video need as input?**

Kandinsky Video requires prompt; it also takes 6 optional inputs, each listed on this page with its allowed values and default.

**Can I call Kandinsky Video from my own code?**

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

## More text to video models

A written scene becomes a clip, many with sound generated in the same pass.

### Gemini Omni 1.2 Flash Text to Video

Google's video model with native dialogue and timed directions, from 360p to 4K.

Text to video / from $0.024 / s

Link: https://flymy.ai/mcp/models/gemini-omni-1-2-flash-t2v/

### Wan 3.0 Text to Video

Alibaba's Wan 3.0: text to video up to 30 seconds, with its own soundtrack.

Text to video / from $0.05 / s

Link: https://flymy.ai/mcp/models/wan-3-0-t2v/

### Seedance 2.5 Text to Video

ByteDance's newest text-to-video: multi-beat scenes up to 30 seconds with sound.

Text to video / from $0.10794 / s

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

### Wan 2.7 Text to Video

Wan 2.7 from text: coherent scenes and natural motion in up to 10 seconds.

Text to video / from $0.10 / s

Link: https://flymy.ai/mcp/models/wan-2-7-t2v/

### Wan 2.6 Text to Video

The previous Wan generation: 2 to 10 second clips with single or multi-shot cuts.

Text to video / from $0.10 / s

Link: https://flymy.ai/mcp/models/wan-2-6-t2v/

### Seedance 2.0 Fast Text to Video

The quick Seedance 2.0 for drafts: prompt-only clips at 480p or 720p with sound.

Text to video / from $0.0538 / s

Link: https://flymy.ai/mcp/models/bytedance-seedance-2-0-fast-text-to-video/

## Go to the source

[Kandinsky Video in the playground →](https://app.flymy.ai/models/flymyai/kandinsky-video), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Text 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.