azure-openai-image¶

Since Docker image version 0.0.33

Azure OpenAI Image Generation Interface.

This provider allows you to generate images using Azure OpenAI’s image generation models like GPT-4o with vision capabilities. It connects to Azure OpenAI deployments and makes them available through the Sample Connector for Bedrock.

Configuration¶

Invoke image generation models via Azure OpenAI API. You can configure Azure OpenAI image model deployments with this provider.

Azure OpenAI Service documentation explains how to use Azure OpenAI API, and what features it supports for image generation.

Key	Type	Required	Description
model	string	Y	The image model to use (e.g., “gpt-image-1”)
apiKey	string	Y	Your Azure OpenAI API key
baseURL	string	Y	The base URL for your Azure OpenAI deployment, including the deployment name (e.g., “https://your-resource-name.openai.azure.com/openai/deployments/your-deployment-name”)
apiVersion	string	Y	The Azure OpenAI API version to use (e.g., “2023-05-15” or “2025-01-01-preview”)

The configuration example:

{
  "model": "gpt-image-1",
  "apiKey": "<your-key>",
  "baseURL": "https://your-resource-name.openai.azure.com/openai/deployments/your-deployment-name",
  "apiVersion": "2025-01-01-preview"
}

Output Results¶

The output follows the standard OpenAI API format for image generation:

{
  "created": 1713184000,
  "data": [
    {
      "b64_json": "iV...."
    }
  ]
}

Usage¶

To generate an image, send a request with a prompt describing the image you want to create. You can also specify parameters like image size, quality, and style.

Example request:

curl http://localhost:8866/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ............" \
  -d '{
    "model": "azure-image",
    "prompt": "A cute cate",
    "n": 1,
    "size": "1024x1024"
  }'