GPT Image 2
State-of-the-art image generation model
OpenAI's GPT Image 2 is a specific image-generation model release used for generating and editing visual assets, including reference-driven product imagery and storyboard frames.
Pricing
Image-token rates in USD per 1M tokens, inferred for GPT Image 2 from the explicit statement that the referenced model's token rates match GPT Image 2. GPT Image 2.5 Flare's same page separately lists text input at $5/1M tokens and cached text input at $1.25/1M; Batch image output is $15/1M tokens.
OpenAI's official GPT Image 2.5 Flare pricing page states that its token rates match GPT Image 2. Image tokens are explicitly priced at $8 per 1M input tokens, $2 per 1M cached input tokens, and $30 per 1M output tokens under Standard processing; output is $15 per 1M tokens with Batch processing. The model page identifies GPT Image 2 as an image-output model.
Model Intelligence
Recent stories
Artificial Analysis says GPT Image 2.5 Flare and Sunburst now hold the top two spots in its image arena. Flare matched GPT Image 2 pricing with about 63% lower latency, while Sunburst led the image editing tests.
Meta launched Muse Image in its apps and previewed Muse Video from the same media-generation family. Meta says Muse Image can reason, search, write code, self-refine, and use test-time compute before generating images.
OpenAI docs say Codex image generation counts against general usage and burns included limits 3-5x faster, while users showed app-server runs with 32 or 64 parallel workers. The workflow turns bulk image or research jobs into quota-backed batches, so teams should watch usage spikes closely.
A day after GPT Image 2 launched, developers and tool vendors posted reproducible workflows for floor plans, QR codes, conference posters, typography, and Figma-style asset generation. The follow-up matters because it shows where text-heavy visual generation is already usable, but also that quality depends heavily on mode choice, image size, and surrounding tool scaffolding.
OpenAI released GPT Image 2 in ChatGPT, Codex, and the API with thinking mode and 2K outputs. Early tests and Arena scores suggest it is usable for slides, UI mockups, and dense infographic layouts.