Weights aren’t public. Use is governed by OpenAI’s terms. Specs from models.dev, last changed Oct 19, 2026. Official source: platform.openai.com.
How good is it?
Public leaderboard scores for gpt-image-1-mini, refreshed daily from Epoch AI and LMArena.
35Quality
Top 65% of the 82 models on the LMArena Text to Image: #54.
Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.
Two edits of the same image; people pick the better one.1,124 rating
Scores from LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits
Where to run it
3 providers sell gpt-image-1-mini through an API. Prices are per million tokens, cheapest first.