Image Generation Server Tool - AI Image Generation for Any Model

Beta

BetaServer tools are currently in beta. The API and behavior may change.

The openrouter:image_generation server tool enables any model to generate images from text prompts. When the model determines it needs to create an image, it calls the tool with a description. OpenRouter executes the image generation and returns the result to the model.

How It Works

You include { "type": "openrouter:image_generation" } in your tools array.
Based on the user’s request, the model decides whether image generation is needed and crafts a prompt.
OpenRouter generates the image using the configured model (defaults to openai/gpt-5-image).
The generated image URL is returned to the model.
The model incorporates the image into its response. It may generate multiple images in a single request if needed.

Quick Start

Configuration

The image generation tool accepts optional parameters to customize the output:

{
  "type": "openrouter:image_generation",
  "parameters": {
    "model": "openai/gpt-5-image",
    "quality": "high",
    "aspect_ratio": "16:9",
    "size": "1024x1024",
    "background": "transparent",
    "output_format": "png"
  }
}

Parameter	Type	Default	Description
`model`	string	`openai/gpt-5-image`	Which image generation model to use. See available image models.
`quality`	string	—	Image quality level (model-dependent, e.g. `"low"`, `"medium"`, `"high"`)
`size`	string	—	Image dimensions (e.g. `"1024x1024"`, `"512x512"`)
`aspect_ratio`	string	—	Aspect ratio (e.g. `"16:9"`, `"1:1"`, `"4:3"`)
`background`	string	—	Background style (e.g. `"transparent"`, `"opaque"`)
`output_format`	string	—	Output format (e.g. `"png"`, `"jpeg"`, `"webp"`)
`output_compression`	number	—	Compression level (0-100) for lossy formats
`moderation`	string	—	Content moderation level (e.g. `"auto"`, `"low"`)

All parameters except model are passed directly to the underlying image generation API. Available options depend on the specific model being used.

Response

When the model calls the image generation tool, it receives a response like:

{
  "status": "ok",
  "imageUrl": "https://..."
}

If generation fails, the response includes an error:

{
  "status": "error",
  "error": "Generation failed due to content policy"
}

Works with the Responses API

The image generation server tool also works with the Responses API:

Pricing

Image generation pricing depends on the underlying model used:

openai/gpt-5-image (default): See model page
openai/gpt-5-image-mini: See model page
openai/gpt-5.4-image-2: See model page
Other models: See the image models list on OpenRouter

The cost is in addition to standard LLM token costs for processing the request and response.

Next Steps

Server Tools Overview — Learn about server tools
Web Search — Search the web for real-time information
Datetime — Get the current date and time
Tool Calling — Learn about user-defined tool calling

Overview

Models & Routing

Features

Privacy

Best Practices

Community

Image Generation

How It Works

Quick Start

Configuration

Response

Works with the Responses API

Pricing

Next Steps

​How It Works

​Quick Start

​Configuration

​Response

​Works with the Responses API

​Pricing

​Next Steps

How It Works

Quick Start

Configuration

Response

Works with the Responses API

Pricing

Next Steps