> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gravitex.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT-Image-2

> OpenAI GPT-Image-2 text-to-image and image-to-image

## Introduction

GPT-Image-2 uses `POST /v1/images/generations` for both text-to-image and image-to-image: omit `image` for T2I; include `image` (URL or Base64) for I2I. Responses use `b64_json` with `usage` token stats.

For full parameters and other image models, see [Image generation](/en/api-reference/endpoint/image-generation).

## Authentication

<ParamField header="Authorization" type="string" required>
  Bearer Token, e.g. `Bearer sk-xxxxxxxxxx`
</ParamField>

## Supported models

| Model ID      | Description                                 |
| ------------- | ------------------------------------------- |
| `gpt-image-2` | OpenAI GPT-Image-2, multi-size including 4K |

## Request examples

<Tabs>
  <Tab title="Text-to-image">
    ```bash theme={null}
    curl -X POST "https://api.gravitex.ai/v1/images/generations" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "gpt-image-2",
        "prompt": "A white cat running under the stars, cyberpunk style",
        "size": "1024x1536",
        "quality": "high",
        "n": 1
      }'
    ```
  </Tab>

  <Tab title="Image-to-image (generations)">
    ```bash theme={null}
    curl -X POST "https://api.gravitex.ai/v1/images/generations" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "gpt-image-2",
        "prompt": "Change the scene to night cyberpunk",
        "image": "https://example.com/input.png",
        "size": "1024x1024",
        "quality": "high"
      }'
    ```
  </Tab>

  <Tab title="Image-to-image (edits)">
    ```bash theme={null}
    curl -X POST "https://api.gravitex.ai/v1/images/edits" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "gpt-image-2",
        "prompt": "Change background to beach sunset",
        "image": "https://example.com/input.png",
        "size": "1024x1024",
        "quality": "high"
      }'
    ```
  </Tab>
</Tabs>

## Common parameters

* **model**: `gpt-image-2`
* **prompt**: Description or edit instruction
* **image**: Reference image for I2I
* **size**: e.g. `1024x1024`, `1024x1536`, `2880x2880` (dimensions multiple of 16)
* **quality**: `low`, `medium`, `high`
* **n**: Number of images (1–10)

See [Image edits](/en/api-reference/endpoint/image-edits) for multipart and more examples; [Image generation](/en/api-reference/endpoint/image-generation) for the full overview.