AI model
The higher-precision image model in OpenAI's GPT-Image-2.5 line, positioned for campaign creative and product imagery that needs tight control across edits.
OpenAI leads on lighting and speed, but the claims that decide whether a team can ship an asset are about holding a subject consistent across turns and leaving untouched regions alone, and neither arrives with a number.
Perspective Coverage
7 publishersReality
OpenAI's guide names Sunburst for editing precision and Flare for speed, and both run from either API. The editing loop, File ID inputs and the action switch exist on the Responses side alone.
Perspective Coverage
7 publishersReality
The 7B open-weight model fits on an RTX 3090 and scores 60.2 on the benchmark its own developers built, against 59.82 for Google's Nano Banana 2.0. The licence shipping with it forbids commercial resale.
Reality
Flare and Sunburst share identical token rates of eight dollars in and thirty out per million, so what a picture costs is set by the quality tier and by however many tokens the model decides to spend.
Reality
Decrypt's rerun gives three of six categories to Google and the rest to OpenAI. The 50% latency cut is OpenAI's own figure, measured against Images 2.0, and the review does not include prices for the two new API tiers.
Reality
OpenAI's newest image models now render inside Adobe's creative studio while more than 70 Adobe tools sit inside ChatGPT, which leaves each company distributing the other and neither owning the moment a creative task starts.
Reality