Generate an Image (Legacy API)

Note: The Hedra v3 API is now available. This guide covers the legacy API and is maintained for existing integrations. For new projects, get started with the Developer Platform →

All examples use the base URL https://api.hedra.com/web-app/public and require an X-API-Key header.

export HEDRA_API_KEY="your_api_key"

Generate an image from a text prompt

curl -X POST https://api.hedra.com/web-app/public/generations \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -d '{
    "type": "image",
    "text_prompt": "A golden retriever sitting in a field of sunflowers",
    "model_slug": "google/nano-banana-pro",
    "aspect_ratio": "16:9",
    "resolution": "2K"
  }'

Required fields

Field	Description
`type`	Set to `"image"`
`text_prompt`	The text description of the image to generate
`model_slug`	The model slug to use (see `GET /models?types=image`)

Optional fields

Field	Description
`aspect_ratio`	e.g. `"16:9"`, `"9:16"`, `"1:1"`
`resolution`	A resolution supported by the selected model
`batch_size`	Generate 1-8 variations at once (default: 1)
`enhance_prompt`	Set to `true` to automatically enhance the prompt

When batch_size is greater than 1, include a generation_ids array containing one client-generated UUID for each variation.

Poll for completion

The response includes a generation id. Poll until status is "complete":

curl https://api.hedra.com/web-app/public/generations/{generation_id}/status \
  -H "X-API-Key: $HEDRA_API_KEY"

When complete, the response includes an asset_id for the generated image.

Available image models

Use GET /models?types=image to list image models and their current slugs, supported resolutions, aspect ratios, and input requirements.

curl "https://api.hedra.com/web-app/public/models?types=image" \
  -H "X-API-Key: $HEDRA_API_KEY"

Getting Started

Guides

API Reference

Generate an Image (Legacy API)

Generate an image from a text prompt

Required fields

Optional fields

Poll for completion

Available image models

​Generate an image from a text prompt

​Required fields

​Optional fields

​Poll for completion

​Available image models

Generate an image from a text prompt

Required fields

Optional fields

Poll for completion

Available image models