> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Grok Imagine Video 1.5

> Text-to-video, image-to-video, and reference-to-video generation with up to seven reference images for consistent characters, up to 15 seconds at 1080p.

![Grok Imagine Video 1.5](https://media.empiriolabs.ai/model-logos/grok-imagine-video-1-5.png)

[xAI](/providers/xai) · Video Generation

`POST /v1/videos/generations`

Text-to-video, image-to-video, and reference-to-video generation with up to seven reference images for consistent characters, up to 15 seconds at 1080p.

## At a glance

| Field               | Value                                                                                |
| ------------------- | ------------------------------------------------------------------------------------ |
| Model id            | `grok-imagine-video-1-5`                                                             |
| Model release date  | 2026-06-16                                                                           |
| Input modalities    | Text, Image                                                                          |
| Output modalities   | Video                                                                                |
| Context window      | -                                                                                    |
| Weight precision    | -                                                                                    |
| Features            | text_to_video, image_to_video, reference_to_video, video_generation                  |
| Native inference    | No                                                                                   |
| New                 | No                                                                                   |
| Supported endpoints | `POST /v1/videos/generations`                                                        |
| Alternate model ids | `grok-imagine-video-1.5`, `xai/grok-imagine-video-1-5`, `xai/grok-imagine-video-1.5` |

## Pricing

| Charge      | Spec       | Rate    |
| ----------- | ---------- | ------- |
| 480p        | per second | \$0.096 |
| 720p        | per second | \$0.168 |
| 1080p       | per second | \$0.300 |
| Image input | per image  | \$0.05  |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/videos/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "grok-imagine-video-1-5", "prompt": "sunrise over the ocean", "duration": 6}'
```

## Parameters

| Parameter          | Type   | Required | Default  | Description                                                                                                                                                     |
| ------------------ | ------ | -------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `prompt`           | string | yes      | -        | Describe the scene, motion, and action to generate.                                                                                                             |
| `mode`             | enum   | no       | `"auto"` | Auto detects from attachments. t2v: text-to-video. i2v: animate one image. r2v: reference-to-video from up to 7 images. · Allowed: `auto`, `t2v`, `i2v`, `r2v`  |
| `image`            | string | no       | -        | Image URL or upload. Optional: one image for image-to-video, up to 7 for reference-to-video. Leave empty for text-to-video.                                     |
| `duration`         | number | no       | `10`     | Length of the generated video in seconds. · Range: 1 – 15                                                                                                       |
| `resolution`       | enum   | no       | `"720p"` | Output resolution. 480p renders fastest, 1080p is the highest definition. Reference-to-video supports up to 720p. · Allowed: `480p`, `720p`, `1080p`            |
| `aspect_ratio`     | enum   | no       | -        | Output aspect ratio. Defaults to the source image aspect ratio for image-to-video, otherwise 16:9. · Allowed: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3` |
| `reference_images` | string | no       | -        | Comma-separated image URLs for reference-to-video (up to 7). Alternative to uploading images.                                                                   |

## Notes

Generates video from a text prompt on its own, from a source image, or from up to seven reference images that keep characters and objects consistent across the shot.

**Modes**

* Text-to-video: send a prompt with no image.
* Image-to-video: add one image and it becomes the starting frame.
* Reference-to-video: add two or more images (up to seven) to carry their subjects into a new scene. Tag them in the prompt as \<IMAGE_1>, \<IMAGE_2>, and so on.

**Example reference-to-video prompt**

```
<IMAGE_1> and <IMAGE_2> walking together through a neon-lit street at night.
```

The mode is detected from what you send, and can be set explicitly with the mode parameter.

**Defaults**

* 10 second duration (1 to 15 seconds supported)
* 720p output (480p, 720p, or 1080p)
* Aspect ratio follows the source image for image-to-video, otherwise 16:9

**Resolution**

1080p is available for text-to-video and image-to-video. Reference-to-video supports up to 720p.

**Controls**

Supports prompt, mode, a source image or reference images (URL or upload), duration, resolution, and aspect ratio.

**Billing**

* Charged per second of generated video at the selected resolution (higher resolutions cost more per second), plus a per-image fee for each image you supply. Text-to-video has no image fee.
* A request that fails validation or errors out before any video is produced is not billed.
* A video that is produced but then blocked by content policy is still billed. This follows xAI usage policy, which charges for the generation even when the output is blocked by the content safety check. Keep prompts and source images within the usage policy to avoid this.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/grok-imagine-video-1-5`.