---
title: Grok Imagine Video 1.5 | Runware Docs
url: https://runware.ai/docs/models/xai-grok-imagine-video-1-5
description: Higher-tier Grok image-to-video generation from a single starting frame with longer durations and stronger output quality
---
# Grok Imagine Video 1.5

![Grok Imagine Video 1.5](https://assets.runware.ai/covers/xai-grok-imagine-video-1-5-preview.jpg)

Grok Imagine Video 1.5 is xAI's newer image-to-video model. It is positioned above the earlier Grok Imagine Video release with higher per-second pricing, supports durations up to 15 seconds, and generates 480p or 720p video from a single still-image starting frame for cinematic clips, animated visuals, and prompt-guided short-form video creation.

- **Status**: live
- **ID**: `xai:grok-imagine@video-1.5`
- Try in Playground
- **Creator**: xAI
- **Release Date**: May 30, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Video, Image to Video, Checkpoint, Audio

## Pricing

$0.08 from, per second · ~49s per request

**Rates**

- 480p · per second: `$0.08`
- 720p · per second: `$0.14`
- 1080p · per second: `$0.25`
- Input image · per input image: `$0.01`

**4 example generations**

- [reference-to-video](https://runware.ai/docs/models/xai-grok-imagine-video-1-5/examples#example-avalanche-forecast-center-logo-loop) · 720p · 5s: `$0.73` (~43s)
- [first-frame](https://runware.ai/docs/models/xai-grok-imagine-video-1-5/examples#example-mobile-knife-sharpening-social-reel) · 720p · 7s: `$0.99` (~42s)
- [multi-speaker-dialogue](https://runware.ai/docs/models/xai-grok-imagine-video-1-5/examples#example-vertical-oyster-hatchery-b-roll) · 720p · 10s: `$1.40` (~55s)
- [text-to-video](https://runware.ai/docs/models/xai-grok-imagine-video-1-5/examples#example-raku-workshop-social-video-ad) · 1080p · 6s: `$1.50` (~3m 42s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Either provide `inputs.frameImages`, or specify `width/height`.

---

Inside `inputs`, `frameImages` cannot be used with `referenceImages`.

---

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.frameImages` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `480p (1:1)` | `480x480` |
| `480p (16:9)` | `848x480` |
| `480p (9:16)` | `480x848` |
| `480p (4:3)` | `640x480` |
| `480p (3:4)` | `480x640` |
| `480p (3:2)` | `720x480` |
| `480p (2:3)` | `480x720` |
| `720p (1:1)` | `720x720` |
| `720p (16:9)` | `1280x720` |
| `720p (9:16)` | `720x1280` |
| `720p (4:3)` | `960x720` |
| `720p (3:4)` | `720x960` |
| `720p (3:2)` | `1088x720` |
| `720p (2:3)` | `720x1088` |
| `1080p (1:1)` | `1424x1424` |
| `1080p (16:9)` | `1904x1072` |
| `1080p (9:16)` | `1072x1904` |
| `1080p (4:3)` | `1648x1232` |
| `1080p (3:4)` | `1232x1648` |
| `1080p (3:2)` | `1744x1152` |
| `1080p (2:3)` | `1152x1744` |

## Notes

Grok Imagine Video 1.5 decides what to generate from the inputs you attach:

- **Text-to-Video:** Provide a prompt on its own.
- **First frame:** Provide `inputs.frameImages` (one item) to start the clip from an image.
- **References:** Provide `inputs.referenceImages` (up to 7) to carry a subject or style into the shot. Reference images and a first frame cannot be combined.

**Speaking characters:** `speech.voices` takes up to three preset voices, and the prompt assigns them by position. `<AUDIO_0>` is the first voice in the array, `<AUDIO_1>` the second, `<AUDIO_2>` the third. Reference images work the same way as `<IMAGE_0>` and up, so a prompt can cast a face and a voice in the same sentence. Voices work on their own or alongside reference images.

**Sizing:** Attaching a first frame or a reference image makes dimensions optional, and `resolution` (`480p`, `720p`, `1080p`) then picks the tier while the source sets the aspect ratio. A prompt-only request needs an explicit `width`/`height` pair from the supported set, and rejects `resolution`.

**Duration:** Any whole number of seconds from 1 to 15.

> [!WARNING]
> Voice IDs are lowercase in the API. The roster matches xAI's text-to-speech voices except for `una`, which this model does not accept.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `7`
- **File size (each)**: `up to 20 MB`

List of reference images (UUID, URL, Data URI, or Base64).

### [frameImages](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `items: 1`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. This model only supports the first frame.

**Allowed values**:

- `first` First frame of the video.
- `0` Frame index 0 (first frame).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `xai:grok-imagine@video-1.5`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `64000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-resolution)

- **Type**: `string`
- **Default**: `480p`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `480p` `720p` `1080p`

### [duration](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-duration)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `15`
- **Default**: `6`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

### [speech](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-speech)

- **Path**: `speech.voices`
- **Type**: `object (1 property)`

Settings for speech generation.

#### [voices](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#request-speech-voices)

- **Path**: `speech.voices`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`

Preset voices the generated speech is performed with. Reference each one in `positivePrompt` as `<AUDIO_0>`, `<AUDIO_1>`, and `<AUDIO_2>`, matching the array index.

## Response Parameters

### [taskType](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [NSFWContent](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/xai-grok-imagine-video-1-5#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/xai-grok-imagine-video-1-5/25baaceb-2acd-4b6c-a9a7-bb3c0d5e6364.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "4de00729-3b40-4a88-9dbf-6566ea80fd1e",
  "model": "xai:grok-imagine@video-1.5",
  "positivePrompt": "A cinematic social media video ad for a nighttime raku pottery workshop, presented as one energetic continuous shot. Begin extremely close inside the glowing mouth of an outdoor ceramic kiln, with a turquoise-and-copper glazed bowl radiating orange heat among the coals. The camera rapidly pulls backward as a pottery artist in a dark heatproof apron lifts the bowl out with long metal tongs; sparks stream toward the lens and the glaze visibly shimmers. Arc smoothly around the artist as they lower the red-hot bowl into a galvanized container of sawdust. A dramatic plume of white smoke and brief amber flames curls around the bowl, then clears just enough to reveal its glossy crackled turquoise surface in the foreground. Rustic workshop courtyard at blue hour, deep navy shadows, intense furnace orange, oxidized copper and turquoise palette, tactile documentary realism, premium craft-commercial lighting, controlled handheld momentum, natural motion blur, realistic fire and smoke physics, strong landscape composition, no captions, no logos, no visible brand names, no cuts.",
  "width": 1904,
  "height": 1072,
  "duration": 6
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/xai-grok-imagine-video-1-5/ae5025d5-540c-414f-88dc-143892c19ec9.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "a3c18d74-5ff8-4547-9b80-07cbc773aed4",
  "model": "xai:grok-imagine@video-1.5",
  "positivePrompt": "The craftsperson smoothly draws the chef’s knife across the wet stone in three controlled strokes, sending a fine ribbon of water and slurry toward the camera. The camera makes a subtle handheld push-in as the polished edge catches the morning light. Without breaking the fluid motion, the craftsperson lifts the knife and slices the nearby ripe tomato into one translucent, paper-thin round. Emphasize precise hand movement, tactile wet scraping sounds, a delicate final slice, crisp editorial realism, cobalt shadows and tangerine gloves. Warm, confident voice-over from <AUDIO_0>: “Your knives aren’t dull forever. We sharpen at your door, while you get dinner ready.” No captions, logos, or on-screen text.",
  "resolution": "720p",
  "duration": 7,
  "speech": {
    "voices": [
      "rex"
    ]
  },
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/cabd294e-acb0-4321-bd61-259acea9a673.jpg"
    ]
  }
}
```

---

### reference-to-video (reference-to-video)

[Watch video](https://assets.runware.ai/examples/xai-grok-imagine-video-1-5/d270a48b-cd24-4fd4-8c8a-108da2c17f1f.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "1e766950-bb36-4d4c-85e0-c09ff8316fa1",
  "model": "xai:grok-imagine@video-1.5",
  "positivePrompt": "Create a broadcast-ready seamless animated logo loop for a regional avalanche forecasting center, using all three reference images together as one coherent visual system. Preserve the exact geometric mountain-and-shield symbol, midnight navy, warm white and safety-orange palette, fine cartographic line weight, matte paper grain and layered snowpack character. Keep the logo centered and generously framed in a locked 16:9 composition. Thin contour lines flow smoothly around the shield like measured elevation data while the stacked bands inside the mountain rise and settle with subtle snow-layer compression. A single safety-orange stratum travels calmly through the mark like a hazard scan, followed by a restrained dusting of fine snow grains. Motion is precise, authoritative and understated rather than dramatic, resolving continuously into a perfect five-second loop with no visible cut. Flat graphic depth, crisp edges, soft embossed shadows, no camera movement, no photoreal landscape, no people, no additional icons and no text.",
  "width": 1280,
  "height": 720,
  "duration": 5,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/853841d2-4e5a-4b76-a80b-2adc16027441.jpg",
      "https://assets.runware.ai/assets/inputs/6b8856ed-025e-46f6-bd48-060ae317193b.jpg",
      "https://assets.runware.ai/assets/inputs/2d0c22a4-00f1-4e03-9d01-5e74ed9bbcb4.jpg"
    ]
  }
}
```

---

### multi-speaker-dialogue (multi-speaker-dialogue)

[Watch video](https://assets.runware.ai/examples/xai-grok-imagine-video-1-5/12c86a44-4278-4688-b973-a69d643efb1b.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "5af2304b-f9f5-43e8-820d-a42a77bee272",
  "model": "xai:grok-imagine@video-1.5",
  "positivePrompt": "A realistic 10-second vertical documentary b-roll shot inside a coastal oyster hatchery at dawn. One continuous gentle handheld-gimbal push past translucent nursery tanks, aeration tubes, and softly bubbling seawater. In the foreground, a young female marine biologist in an orange waterproof apron studies a digital salinity meter while an older male hatchery manager in navy coveralls adjusts a stainless-steel flow valve beside her. Cool cyan ambient light, muted sea-green tanks, warm sunrise spilling through high windows, natural condensation and authentic working details. Clearly distinguish the two speakers and show subtle natural lip movement. The female biologist looks at the meter and says calmly: <AUDIO_0> \"Salinity is holding at twenty-eight.\" The male manager checks the tank, then replies: <AUDIO_1> \"Good. Open the nursery flow and log this batch.\" Observational editorial stock-footage style, credible aquaculture procedure, restrained performances, realistic water motion, no logos, no captions, no on-screen text.",
  "width": 720,
  "height": 1280,
  "duration": 10,
  "speech": {
    "voices": [
      "iris",
      "atlas"
    ]
  }
}
```