Skip to content
AI Primer

GPT Image 2

State-of-the-art image generation model

OpenAI's state-of-the-art image generation model for fast, high-quality image generation and editing. The official release announcement says it is designed for complex visual tasks with stronger editing, better layouts, improved text rendering, and more reliable instruction-following, and that developers can use it in the API and Codex starting April 21, 2026.

Pricing

Model profile · Current snapshot
Input / 1M
$0.15
Output / 1M
$0.60
Blended / 1M
$0.262
Output TPS
73.36
TTFT (s)
0.49

Model Intelligence

Arena ranking
13
Benchmarkable
Yes
Model level
release
Intelligence Index
12.6
Math Index
14.7
MMLU Pro
0.65
GPQA
0.43
HLE
0.04
LiveCodeBench
0.23
SciCode
0.23
MATH-500
0.79
AIME
0.12
AIME 2025
0.15
IFBench
0.31

Recent stories

4 linked stories
releasePRIMARY2026-06-07
OpenAI launches gpt-image-2 API with 1024×1024 pricing from $0.006 to $0.211

OpenAI exposed gpt-image-2 through the API with model-card details and concrete 1024×1024 pricing tiers, from $0.006 at low quality to $0.211 at high quality. The release gives engineers a new image endpoint with stronger instruction following and text rendering, but output-cost tradeoffs remain material at higher settings.

workflowSECONDARY2026-04-26
Codex app-server supports 32-64 parallel jobs and burns limits 3-5x faster

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.

newsPRIMARY2026-04-22
Developers report QR codes, floor plans, and poster workflows one day after GPT Image 2 launch

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.

releasePRIMARY2026-04-21
OpenAI launches GPT Image 2 with thinking, 2K outputs, and text rendering gains

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.

AI PrimerAI Primer

Your daily guide to AI tools, workflows, and creative inspiration.

© 2026 AI Primer. All rights reserved.