GPT Image 2.5 Flare

GPT Image 2.5 Flare was released on 8 September 2026 together with GPT Image 2.5 Sunburst. OpenAI calls it its fastest model for high-quality, everyday image generation; it takes text and image inputs and returns images, through the Image API or as the model behind the Responses API image generation tool. The two models are priced identically, so the choice between them is not a budget decision. OpenAI rates Flare 'higher' on performance and 'very fast' on speed, against 'highest' and 'medium' for Sunburst - in other words, Flare gives up the top of the quality scale to run faster at the same cost per token. Both models support the new xhigh and max quality settings alongside low, medium, high and auto, and both use GPT Image 2 token rates: $5 per million text input tokens, $8 per million image input tokens and $30 per million image output tokens. OpenAI notes that the GPT Image 2 calculator does not estimate how many tokens the 2.5 models consume.

▸Videos

No videos yet.

▸Reviews