Product · Image generation
One API for every image model.
Generate and edit images at provider prices.
LLM Gateway puts the image models of every major lab behind one OpenAI-compatible endpoint. Pick a model per request, pay per image, and see what each one cost.
An image in one request
The same request as OpenAI's images API. Change the base URL and the key, then pick any model from the table below.
curl -X POST "https://api.llmgateway.io/v1/images/generations" \
-H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "<image-model-id>",
"prompt": "A lighthouse on a cliff at dawn, watercolor",
"size": "1024x1024"
}'Image generation pricing
The lowest price of one image for each model, across the providers that serve it today. Larger sizes and higher quality cost more; each model page has the full list.
Pricing and availability as of
Compare every option on the text-to-image and image-to-image pages.
Built for apps that make a lot of images
One API for every image model
Call any image model in the catalogue with the same request. Switching models is a one-word change, not a new SDK.
Generate and edit
OpenAI-compatible /v1/images/generations and /v1/images/edits, plus image output in /v1/chat/completions for conversational edits.
Failover across providers
When several providers serve a model, a request that names only the model is retried on another one if the first fails.
Provider prices, per image
Each image is billed at the provider's rate for its size and quality. The table below is read from the live catalogue.
Cost on every response
Image responses carry a usage object with the billed cost, and the dashboard breaks spend down by model, provider and API key.
Keys and limits per project
Give each app or customer its own API key with a spending limit, and bring your own provider keys when you have them.
Ship image generation today
Create a key, send one request, and switch models whenever a better one ships.