Models / Images
GPT Image 2.5 Flare
By OpenAI, in Claude, ChatGPT, Cursor, Claude Code, and the API. The default for images.
OpenAI's everyday image model: photoreal product shots and legible text in images. Second in blind tests, behind only Sunburst.
- Made by
- OpenAI
- Type
- Images
- Price band
- Standard
- Blind tests
- #2 on Artificial Analysis's text-to-image arena, September 2026
- Shapes
- square
- Reference image
- Edits or builds on your image
- Model id
- gpt-image-2.5-flare
Ask for it by name
It's the default, so your AI uses it for images unless you name another.
youUse GPT Image 2.5 Flare to make a square photo of a matte-black wristwatch on wet slate, soft rim light.
A Studio month (3,000 credits) covers about 335 images with GPT Image 2.5 Flare, or a mix with any other model. See plans.
From your own code
The same key your assistant uses works as a bearer token. See the docs.
curl https://getstudiopass.com/v1/generations \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"modality":"image","model":"gpt-image-2.5-flare","prompt":"A lighthouse at dawn, watercolor"}'