# Grok Imagine Video 1.5 MCP and API by xAI | FlyMy.AI

> xAI Grok Imagine Video 1.5 makes a 1 to 15 second video with synced sound from a prompt, a first-frame picture or up to 14 reference pictures.

Page: https://flymy.ai/mcp/models/grok-imagine-video-1-5/

MCP / Models / Text to video

# Grok Imagine Video 1.5 MCP: clips with synced sound

xAI Grok Imagine Video 1.5 makes a 1 to 15 second video with synced sound from a prompt, a first-frame picture or up to 14 reference pictures. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Grok Imagine Video 1.5](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#start) [Inputs and price](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#inputs)

No API key, from $0.08 / s, Text and image to video, xAI, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Grok Imagine Video 1.5 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/grok-imagine-video-1-5.md. Help me connect the FlyMy.AI MCP to this assistant, then run Grok Imagine Video 1.5 (flymyai/grok-imagine-video-1_5) for this task: Make a 10-second 9:16 video of a fox running through fresh snow at sunrise with Grok Imagine Video 1.5 at 1080p.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/grok-imagine-video-1-5.md)

## What Grok Imagine Video 1.5 does

Describe the shot, the camera and the sound in prompt. Add image to start from your picture, which becomes the first frame and sets the shape of the video, or reference_images, up to 14 links that supply the people, products and places, named in the prompt as IMAGE_0, IMAGE_1 and so on, each in angle brackets. duration is 1 to 15 seconds (5 by default), resolution is 480p, 720p (the default) or 1080p, although reference pictures go up to 720p, aspect_ratio is 16:9 by default or one of eight other shapes, and generate_audio is on by default, with lip-synced speech. Billing counts the seconds made at the rate of the resolution, and each picture you give adds a small charge once per request. It does not edit or extend an existing video and takes no last frame or voice references.

## Grok Imagine Video 1.5 inputs

Every input of `flymyai/grok-imagine-video-1_5` as its live schema lists them. Returns `video` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#input-prompt) `prompt` | string required What happens in the video, the camera and the sound. With reference pictures, name them in the prompt as IMAGE_0, IMAGE_1 and so on, each in angle brackets |
| [#](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#input-image) `image` | file optional Allowed: image file, as a URL or upload First frame (JPEG, PNG or WEBP): the video starts from this picture and keeps its shape. Adds $0.01 |
| [#](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#input-reference_images) `reference_images` | string optional Up to 14 reference image URLs (a JSON array or one URL) that supply people, products and places without fixing the first frame; 720p at most. Each adds $0.01 |
| [#](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#input-duration) `duration` | integer optional Allowed: 1 to 15 Default: `5` Length in seconds, 1-15; billed per second |
| [#](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#input-resolution) `resolution` | string optional Allowed: 480p, 720p, 1080p Default: `720p` Billed per second: $0.08 at 480p, $0.14 at 720p, $0.25 at 1080p. References go up to 720p |
| [#](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#input-aspect_ratio) `aspect_ratio` | string optional Allowed: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9, 5:2 Default: `16:9` Shape of the video; a first frame sets its own shape |
| [#](https://flymy.ai/mcp/models/grok-imagine-video-1-5/#input-generate_audio) `generate_audio` | boolean optional Default: `true` Make sound with the video, with lip-synced speech. No extra charge |

## Ask your agent

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

**“Make a 10-second 9:16 video of a fox running through fresh snow at sunrise with Grok Imagine Video 1.5 at 1080p.”** runs `flymyai/grok-imagine-video-1_5`

**“Write and render a short ad for a skincare serum with Grok Imagine Video 1.5: three quick shots ending on the product.”** runs `flymyai/grok-imagine-video-1_5`

**“Animate the photo I attach with Grok Imagine Video 1.5: the person turns and smiles at the camera.”** runs `flymyai/grok-imagine-video-1_5`

## Grok Imagine Video 1.5 price

From $0.08 per second of duration, depending on resolution; each picture given (a first frame or a reference) adds $0.01. A run at the default settings costs $0.70. A run costs $0.08 to $3.76, depending on resolution and duration. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

| Setting | Price |
|---|---|
| resolution 480p | $0.08 per second |
| resolution 720p | $0.14 per second |
| resolution 1080p | $0.25 per second |

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

## Call Grok Imagine Video 1.5 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/grok-imagine-video-1_5",
  "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/grok-imagine-video-1_5/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/grok-imagine-video-1_5/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 Grok Imagine Video 1.5

**Do I need an xAI API key for Grok Imagine Video 1.5?**

No. Grok Imagine Video 1.5 runs on FlyMy.AI's account, so you need no xAI key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Grok Imagine Video 1.5 cost?**

From $0.08 per second of duration, depending on resolution; each picture given (a first frame or a reference) adds $0.01. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use Grok Imagine Video 1.5 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 10-second 9:16 video of a fox running through fresh snow at sunrise with Grok Imagine Video 1.5 at 1080p." Your agent reads the inputs with get_model_schema and runs flymyai/grok-imagine-video-1_5 with run_model.

**What does Grok Imagine Video 1.5 need as input?**

Grok Imagine Video 1.5 requires prompt; it also takes 6 optional inputs, each listed on this page with its allowed values and default.

**Can I call Grok Imagine Video 1.5 from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/grok-imagine-video-1_5/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.

### FLUX 3 Max Text to Video

Post-trained FLUX 3 Video: cinematic clips up to 20 seconds with native sound.

Text to video / from $0.17 / s

Link: https://flymy.ai/mcp/models/flux-3-max-text-to-video/

### FLUX 3 Video Text to Video

Black Forest Labs' video model from text: 5 to 20 second clips with spoken lines, plus cheap drafts.

Text to video / from $0.15 / s

Link: https://flymy.ai/mcp/models/flux-3-video-t2v/

### HeyGen Video 1 Text to Video

HeyGen's video model: presenter, product and training clips with sound, up to 30 s.

Text to video / from $0.02 / s

Link: https://flymy.ai/mcp/models/heygen-video-1-text-to-video/

### Kling 4.0 Flash Text to Video

The fast Kling 4.0 tier: 720p drafts and social clips with sound, up to 20 seconds.

Text to video / $0.094 / s

Link: https://flymy.ai/mcp/models/kling-4-0-flash-text-to-video/

### Kling 4.0 Text to Video

Kuaishou's Kling 4.0 from a prompt: up to 30 seconds with stereo sound and in-sync dialogue.

Text to video / from $0.157 / s

Link: https://flymy.ai/mcp/models/kling-4-0-text-to-video/

### LTX 2.5 Fast Text to Video

LTX 2.5 in its speed mode: drafts and social clips of up to 20 seconds, or up to 4K for 10 seconds.

Text to video / from $0.09 / s

Link: https://flymy.ai/mcp/models/ltx-2-5-fast-text-to-video/

## Go to the source

[Grok Imagine Video 1.5 in the playground →](https://app.flymy.ai/models/flymyai/grok-imagine-video-1_5), [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 2026-11-18: 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.
