Skip to content

Generate a cover image with AI​

POST
/images/generate

Generates a landscape campaign cover from a prompt (the first 500 characters are used, wrapped in a fixed style prompt). Requires a bearer session.
With the default gpt-image-* model the image is stored on the platform CDN immediately and persisted is true; that path is also gated by features.image_uploads and answers 403 when the flag is off. With a dall-e-* model the URL is OpenAI's temporary one (persisted: false) and should be copied with POST /images/save-from-url.
Limited to 10 generations an hour and 30 a day per user; past either limit the answer is 429 with Retry-After. Errors from the image provider are not passed through: a prompt the provider refuses answers 400, a temporarily unavailable provider 503, and any other provider failure 502, each with a generic message.

Authorizations​

BearerAuth

In the browser, authentication rides on the httpOnly session cookies set by /cognito/signin or the Google / Apple sign-in at /cognito/oauth/{provider}. For scripts and for Swagger UI testing, paste an API key (fh_live_…, created with POST /api-keys); a Cognito JWT is accepted too. Sign-in does not return a token in its body.

Type
HTTP (bearer)

Request Body​

application/json
JSON
{
"prompt": "string"
}

Responses​

Generated image

application/json
JSON
{
"url": "string",
"revisedPrompt": "string",
"persisted": true
}

Playground​

Server
Authorization
Body

Samples​

Powered by VitePress OpenAPI

Built with VitePress