Text-to-image · all categories · quality=max
95% CI 1,197.2–1,217.2 · n=12,120
General-purpose GPT Image 2.5 tier with transparent output, custom dimensions and five explicit quality levels.
OpenAI's default image model for most applications. Fast, high-quality generation with natural lighting, rich textures, and support for complex layouts including transparent backgrounds.
Text-to-image · all categories · quality=max
95% CI 1,197.2–1,217.2 · n=12,120
Input/reference charges are listed separately. · Billing component; not a complete generation price.
openai/gpt-image-2.5-flareopenai/gpt-image-2.5/flare/text-to-imageac3abe51-14ca-4c04-b215-01a85f3a36acUpdated Oct 18, 2026
Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.
Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.
Trades longer generation time for intricate detail; supports transparent backgrounds and quality levels through max.
OpenAI's GPT Image 1 generates and edits images via the dedicated Images API. Features accurate text rendering, transparent backgrounds, and up to 16 reference images for edits.