# Grok Imagine Image

> Generate high-quality images from a text prompt, with aspect-ratio control and a standard or high-resolution (2k) output.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/xai/grok-imagine/image`
- **Model ID**: `xai/grok-imagine/image`
- **Category**: text-to-image
- **Kind**: inference
- **Tags**: text-to-image, xai, grok, grok-imagine, image-generation

## Pricing

- **Price**: $0.02 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/xai/grok-imagine/image` with a JSON body. The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/xai/grok-imagine/image/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/xai/grok-imagine/image/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/xai/grok-imagine/image/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`prompt`** (`string`, _required_):
  Text description of the desired image.

- **`num_images`** (`integer`, _optional_):
  The number of images to generate. Each generated image is billed.
  - Default: `1`
  - Range: `1` to `4`

- **`resolution`** (`ResolutionEnum`, _optional_):
  Output resolution tier: 1k (standard) or 2k (high resolution).
  - Default: `"1k"`
  - Options: `"1k"`, `"2k"`

- **`aspect_ratio`** (`AspectRatioEnum`, _optional_):
  Aspect ratio (width:height) of the generated image.
  - Default: `"1:1"`
  - Options: `"2:1"`, `"20:9"`, `"19.5:9"`, `"16:9"`, `"4:3"`, `"3:2"`, `"1:1"`, `"2:3"`, `"3:4"`, `"9:16"`, `"9:19.5"`, `"9:20"`, `"1:2"`

- **`output_format`** (`OutputFormatEnum`, _optional_):
  The image file format of the output.
  - Default: `"jpeg"`
  - Options: `"jpeg"`, `"png"`, `"webp"`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "a hand-lettered vintage travel poster for Kyoto in autumn, warm muted palette, bold legible typography",
  "num_images": 1,
  "resolution": "1k",
  "aspect_ratio": "16:9",
  "output_format": "jpeg"
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/GBWrXTn1mKp6CTxC0PzFn.jpeg"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/xai/grok-imagine/image \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "a hand-lettered vintage travel poster for Kyoto in autumn, warm muted palette, bold legible typography",
  "num_images": 1,
  "resolution": "1k",
  "aspect_ratio": "16:9",
  "output_format": "jpeg"
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("xai/grok-imagine/image", {
  input: {
  "prompt": "a hand-lettered vintage travel poster for Kyoto in autumn, warm muted palette, bold legible typography",
  "num_images": 1,
  "resolution": "1k",
  "aspect_ratio": "16:9",
  "output_format": "jpeg"
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "xai/grok-imagine/image",
        arguments={
  "prompt": "a hand-lettered vintage travel poster for Kyoto in autumn, warm muted palette, bold legible typography",
  "num_images": 1,
  "resolution": "1k",
  "aspect_ratio": "16:9",
  "output_format": "jpeg"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/xai/grok-imagine/image)
- [OpenAPI Schema](https://modelrunner.ai/models/xai/grok-imagine/image/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/xai/grok-imagine/image/llms.txt)