GPT Image 2.5 Flare

GPT Image 2.5 Flare (gpt-image-2.5-flare) is OpenAI's faster image model for everyday generation. It takes text and image input and returns an image. OpenAI describes higher quality than GPT Image 2 and about 50% lower latency. Standard token rates match GPT Image 2: text input $5 per 1M tokens ($1.25 cached), image input $8 ($2 cached), and image output $30. Text output is not billed.