Generates images from text prompts using OpenAI-compatible format.
Note: Azure OpenAI deployments are also supported via the Azure integration endpoint.
Note: This endpoint also works without the /v1 prefix (e.g., /openai/images/generations).
Model identifier
Text prompt to generate image
Number of images to generate
1 <= x <= 10Size of the generated image
256x256, 512x512, 1024x1024, 1792x1024, 1024x1792, 1536x1024, 1024x1536, auto Quality of the generated image
standard, hd Style of the generated image
natural, vivid Format of the response. This parameter is not supported for streaming requests.
url, b64_json User identifier for tracking
Whether to stream the response. When true, images are sent as base64 chunks via SSE.
Fallback models to try if primary model fails
Successful response. Returns JSON for non-streaming requests, or Server-Sent Events (SSE) stream when stream=true.
When streaming, each event contains a chunk of the image as base64 data, with the final event having type image_generation.completed.