# GPT Image 2

> OpenAI's state-of-the-art image generation model. Create and edit images from text with strong instruction following, sharp text rendering, and detailed editing.

- **Provider**: replicate
- **Model ID**: openai/gpt-image-2
- **Category**: image_generation
- **Credits**: 480 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

- `openai_api_key` (string, optional): Your OpenAI API key (optional - uses proxy if not provided)
- `aspect_ratio` (string, optional): The aspect ratio of the generated image (Default: `1:1`; Options: `1:1`, `3:2`, `2:3`)
- `input_images` (array, optional): A list of images to use as input for the generation (for editing or composing) (Default: `[]`)
- `number_of_images` (integer, optional): Number of images to generate. Limited to 1 — for multiple images, call the API multiple times. (Default: `1`; Range: min: 1, max: 1)
- `output_format` (string, optional): Output image format (Default: `webp`; Options: `webp`, `png`, `jpeg`)
- `output_compression` (integer, optional): Compression level (0-100%) for webp/jpeg output (Default: `90`; Range: min: 0, max: 100)
- `user_id` (string, optional): An optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.
- `background` (string, optional): Set whether the background is opaque or choose automatically (transparent backgrounds not supported) (Default: `auto`; Options: `auto`, `opaque`)
- `moderation` (string, optional): Content moderation level (Default: `auto`; Options: `auto`, `low`)
- `prompt` (string, **required**): A text description of the desired image
- `quality` (string, optional): The quality of the generated image. Higher quality is sharper but slower and more expensive. (Default: `auto`; Options: `low`, `medium`, `high`, `auto`)

## Example Request

```json
{
  "model": "openai/gpt-image-2",
  "input": {
    "aspect_ratio": "3:2",
    "number_of_images": 1,
    "output_format": "webp",
    "output_compression": 90,
    "background": "auto",
    "prompt": "A photorealistic close-up portrait of an elderly Japanese ceramicist with deep wrinkles and a warm smile, carefully inspecting a freshly glazed tea bowl in his rustic sun-drenched workshop. Soft golden hour light streams through a window.",
    "quality": "high"
  }
}
```

## 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

image-generation, text-to-image, image-editing, openai, typography, photorealistic, text-rendering, character-consistency, frontier

## Documentation

https://replicate.com/openai/gpt-image-2