Image Generation Models

AI models for creating, editing, and understanding images

12 models12 makersData through Sep 16, 2026

Image · Stability AI

sd3.5-flash
Available
Text to Image
TokenLab price-30% Discount
$0.0175/image
Official price
$0.025/image
sd3.5-large
Available
Text to Image
TokenLab price-30% Discount
$0.0455/image
Official price
$0.065/image
sd3.5-large-turbo
Available
Text to Image
TokenLab price-30% Discount
$0.028/image
Official price
$0.04/image
sd3.5-medium
Available
Text to Image
TokenLab price-30% Discount
$0.0245/image
Official price
$0.035/image
stability-control-sketch
Available
Image to ImageImage Edit
TokenLab price-30% Discount
$0.035/image
Official price
$0.05/image
stability-control-structure
Available
Image to ImageImage Edit
TokenLab price-30% Discount
$0.035/image
Official price
$0.05/image
stability-inpaint
Available
Image to ImageImage Edit
TokenLab price-30% Discount
$0.035/image
Official price
$0.05/image
stability-style-guide
Available
Image to ImageImage Edit
TokenLab price-30% Discount
$0.035/image
Official price
$0.05/image
stability-upscale-conservative
Available
Image to ImageImage Edit
TokenLab price-30% Discount
$0.28/image
Official price
$0.40/image
stability-upscale-fast
Available
Image to ImageImage Edit
TokenLab price-30% Discount
$0.014/image
Official price
$0.02/image
stable-image-core
Available
Text to Image
TokenLab price-30% Discount
$0.021/image
Official price
$0.03/image
stable-image-ultra
Available
Text to Image
TokenLab price-30% Discount
$0.056/image
Official price
$0.08/image

All model series

2 series

Choosing the right image generation model

The right model balances task fit, output quality, latency, and price.

Selection signals

  • Match the model to the input and output you actually need.
  • Compare models that use the same pricing unit.
  • A small test reveals quality and latency differences that a catalog cannot.

FAQ

What makes a good image generation model?

A strong fit matches the task, quality bar, latency target, and budget. A small evaluation set makes quality and reliability differences easier to see.

Can I switch models later?

Yes. Keep the public model ID and request format explicit, and compare alternatives on the same tasks.