
GPT Image 2.5
Split image line: Flare for speed, Sunburst for editing precision.
About
GPT Image 2.5, released September 8, 2026, continues OpenAI's image model line as two distinct API models rather than one. GPT-Image-2.5 Flare is the fast, everyday default for high-quality generation, while GPT-Image-2.5 Sunburst is tuned for editing precision and is the default on the images edits endpoint. Both share the same token pricing ($8 per million image input tokens, $30 per million output tokens at standard rates).
Quality now goes up to max, edits accept up to 16 input images, and output reaches 3840x2160. Neither 2.5 model supports the Batch API, which remains available on GPT Image 2, so high-volume batch workflows should stay on the base model name. Requests to the gpt-image-2 model name are served by 2.5 Flare at the same price, keeping existing integrations working.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 9/10
Scored 9/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 98; Trending score 88/100 from researcher assessment.