# Grok Imagine Image Quality

> xAI's highest-fidelity Grok Imagine image model. Best output quality in the Grok Imagine family for detailed, polished renders.

- **Provider**: xai-image
- **Model ID**: xai/grok-imagine-image-quality
- **Category**: image_generation
- **Credits**: 120 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `resolution` (string, optional): Output resolution tier. 2k is billed at a higher rate; omitted defaults to 1k. (Options: `1k`, `2k`)
- `prompt` (string, **required**): Text prompt for image generation.
- `n` (integer, optional): Number of images to generate. Billed per image. (Default: `1`; Range: min: 1, max: 10)
- `aspect_ratio` (string, optional): Aspect ratio of the generated image. (Default: `auto`; Options: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `2:1`, `1:2`, `19.5:9`, `9:19.5`, `20:9`, `9:20`, `auto`)

## Example Request

```json
{
  "model": "xai/grok-imagine-image-quality",
  "input": {
    "prompt": "An ultra-detailed studio photograph of a vintage mechanical watch on dark velvet, macro lens, dramatic side lighting"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

xai, grok, image-generation, text-to-image, high-quality

## Documentation

https://docs.x.ai/developers/model-capabilities/images/generation