Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.compose.market/llms.txt

Use this file to discover all available pages before exploring further.

Image generation uses OpenAI-style request bodies and provider-specific adapter execution.
MethodPathDescription
POST/v1/images/generationsGenerate images from text and optional image input.
POST/v1/images/editsEdit an input image with a prompt.
POST/external/v1/images/generationsExternal OpenAI-compatible image generation.

​
Generate an image

curl https://api.compose.market/v1/images/generations \
  -H "Authorization: Bearer $COMPOSE_MARKET_API_KEY" \
  -H "Content-Type: application/json" \
  -H "x-chain-id: 43113" \
  -d '{
    "model": "nano-banana",
    "prompt": "A product diagram of an HTTP payment flow",
    "size": "1024x1024",
    "n": 1
  }'
The response returns data[] with either b64_json or url, depending on provider output.

​
Edit an image

{
  "model": "gpt-image-2",
  "image": "data:image/png;base64,...",
  "prompt": "Make the labels easier to read.",
  "size": "1024x1024"
}

​
Metering

Image metering uses provider output evidence such as generated image count, duration, generated units, or provider billing metrics when available.