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

# Image Generation

> Let models create images through A Phaseo server tool.

Use `phaseo:image_generation` when the model should be able to create an image while it is answering. Phaseo exposes a managed tool to the model, executes the image request server-side, and feeds the image result back into the model loop.

## Request

```bash theme={null}
curl https://api.phaseo.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5-nano",
    "input": "Design a wide product concept image for a compact desktop synthesizer.",
    "tools": [
      {
        "type": "phaseo:image_generation",
        "parameters": {
          "model": "openai/gpt-image-2",
          "quality": "high",
          "aspect_ratio": "16:9",
          "output_format": "png"
        }
      }
    ]
  }'
```

## Parameters

| Parameter            | Type    | Description                                                                                                             |
| -------------------- | ------- | ----------------------------------------------------------------------------------------------------------------------- |
| `model`              | string  | Optional image-capable model ID. Defaults to `openai/gpt-image-2` when neither the tool nor tool call provides a model. |
| `quality`            | string  | Optional provider quality hint, such as `low`, `medium`, or `high`.                                                     |
| `size`               | string  | Optional image size hint.                                                                                               |
| `aspect_ratio`       | string  | Optional aspect ratio, such as `1:1`, `16:9`, or `9:16`.                                                                |
| `background`         | string  | Optional background mode hint.                                                                                          |
| `output_format`      | string  | Optional output format, such as `png`, `jpeg`, or `webp`.                                                               |
| `output_compression` | integer | Optional provider compression hint.                                                                                     |
| `moderation`         | string  | Optional provider moderation hint.                                                                                      |

The model supplies the final `prompt` when it calls the tool. Tool-level parameters provide defaults and constraints for that call.

The tool call may also send `description` instead of `prompt`. Phaseo treats `description` as a prompt alias for compatibility with model-generated image descriptions.

## Tool Result

The result is returned to the model as JSON:

```json theme={null}
{
  "status": "ok",
  "model": "openai/gpt-image-2",
  "imageUrl": "https://...",
  "mime_type": "image/png"
}
```

Some providers return base64 image data instead:

```json theme={null}
{
  "status": "ok",
  "model": "openai/gpt-image-2",
  "b64_json": "...",
  "mime_type": "image/png"
}
```

## Usage And Pricing

Image generation usage is included in the parent response usage when the image model reports token usage. Phaseo also records:

```json theme={null}
{
  "usage": {
    "server_tool_use": {
      "image_generation_requests": 1
    }
  }
}
```

Pricing cards can bill this with the `server_tool_image_generation_requests` meter. The underlying image model usage can still be billed through its normal model pricing.

## Related

* [Server Tools](./index)
* [Tool Calling](../tool-calling)