VercelVercel
Menu

Image Generation

Last updated

Image generation

Generate images using AI models that support multimodal output through the OpenAI-compatible API. This feature allows you to create images alongside text responses using models like Google's Gemini 2.5 Flash Image.

Endpoint
Parameters

To enable image generation, include the parameter in your request:

  • (array): Array of strings specifying the desired output modalities. Use for both text and image generation, or for image-only generation.
Example requests
Response format

When image generation is enabled, the response separates text content from generated images:

Response structure details

  • : Contains the text description as a string
  • : Array of generated images, each with:
    • : Always
    • : Base64-encoded data URI of the generated image

Streaming responses

For streaming requests, images are delivered in delta chunks:

Handling streaming image responses

When processing streaming responses, check for both text content and images in each delta:

Image generation support: Currently, image generation is supported by Google's Gemini 2.5 Flash Image model. The generated images are returned as base64-encoded data URIs in the response. For more detailed information about image generation capabilities, see the Image Generation documentation.

Was this helpful?

supported.