Image MODEL
The December 2025 tier, still in the API and faster than 2. Good text rendering, but without the reasoning pass, so complex layout instructions have to be spelled out.
MAKER
OpenAI
ACCESS
api
TRAINABLE
No
GEOMETRY
3 / 5
Tasks
Text to Image
Image to Image
Inpainting
PUBLICATION
ArchitectureLM
SUBJECT
AI in architecture
NEWSLETTER
Weekly, free
CONTACT
hello@architecturelm.com
© 2026 ArchitectureLM. All rights reserved.