Image Generation
Generate an image from a text prompt.
request_id you can poll via GET /api/v2/jobs/{request_id} or receive via webhooks / WebSockets.
slug, check specific limits and features, and verify LoRA availability. Please omit the LoRA parameter by default during initial testing.Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
application/json Body
Image generation parameters
The main prompt for image generation
"A beautiful sunset over mountains"
The model to use for image generation. Available models can be retrieved via the GET /api/v1/client/models endpoint.
"Flux1schnell"
Width of the generated image in pixels
512
Height of the generated image in pixels
512
Guidance scale for the generation
7.5
Number of inference steps
20
Random seed for generation
42
Elements to avoid in the generated image
"blur, darkness, noise"
Array of LoRA models to apply
Quality tier, for models that support one (e.g. gpt-image: low/medium/high/auto). Only the values listed in that model's available options are accepted; ignored for models without a quality tier.
"medium"
Optional HTTPS URL to receive webhook notifications for job status changes (processing, completed, failed). Must be HTTPS. Max 2048 characters. See Webhook Documentation for payload structure and authentication details.
2048"https://your-server.com/webhooks/deapi"
Optional per-request HMAC secret (min. 32 chars) used to sign the webhook callback. When present, overrides the account-default webhook secret. Requires webhook_url to also be set.
32 - 255"a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5"
Response
ID of the inference request.
Information from success endpoint