Frontier image generation model with both text-to-image and image-to-image capabilities. Understands context and makes editing easy.
Added May 29, 2025
Approx. Price
$0.040 per image
Model Type
both
Preview Examples
2
Generation controls available for this model.
Images Per Run
Up to 4
Resolution Options
10
auto (Auto (let API decide)), 1344x640 (Landscape (21:9)), 1024x576 (Landscape (16:9)) +7 more
Tunable Settings
6
Guidance Scale
Default
3.5
How closely the model follows your prompt
Inference Steps
Default
28
Number of inference steps to perform
Max Mode
Default
No
Options (2)
On, Off
Enable Max mode for more complex tasks (doubles cost)
Number of Images
Default
1
Resolution
Default
auto
Options (10)
auto (Auto (let API decide)), 1344x640 (Landscape (21:9)), 1024x576 (Landscape (16:9)), 1024x768 (Landscape (4:3)) +6 more
Safety Tolerance
Default
5
Human preference benchmarks sourced from Artificial Analysis.
No Artificial Analysis benchmark data is available yet for this model.
Artificial Analysis API
Put a donut next to the flour
Default
