Not established from the available sources.
OPENAI · MODEL RELEASE TRACKER
GPT-Image-2.5
An OpenAI image-focused model version — described by OpenAI as providing "precise visuals" and announced as part of the Higgsfield update.CURRENT SNAPSHOT1/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
ModalityVisual / image generation (described in the announcement as providing visuals).
Not established from the available sources.
Not established from the available sources.
VERIFIABLE FACTS
Every value stays attached to a source and date.
CAPABILITIES · Image and cinematic video ad generationDEVELOPER CLAIM
OpenAI's page describes GPT-Image-2.5 as helping creators turn ideas into detailed images and cinematic video ads.
MODALITIES · ModalityDEVELOPER CLAIM
Visual / image generation (described in the announcement as providing visuals).
RELEASE · AnnouncementDEVELOPER CLAIM
Announced by OpenAI in the Higgsfield update (published 2026-10-13) as part of features including longer videos and precise visuals.
CAPABILITIES · Capability — precise visualsDEVELOPER CLAIM
Described by OpenAI as providing "precise visuals."
WHAT CHANGED
Stored passport versions, without reconstructed history.
RELEASE · Announcement+ Announced by OpenAI in the Higgsfield update (published 2026-10-13) as part of features including longer videos and precise visuals.
MODALITIES · Modalities: images and video− The excerpt indicates GPT-Image-2.5 is used to produce images and cinematic video ads (image and video modalities).
CAPABILITIES · Capability — precise visuals+ Described by OpenAI as providing "precise visuals."
MODALITIES · Modality+ Visual / image generation (described in the announcement as providing visuals).