OpenAI GPT Image 2
OpenAI's state-of-the-art image generation model with precise instruction-following for both text-to-image and image editing.
OpenAI's GPT Image 2 is a cloud image-generation model. It generates images from a text prompt, and can take reference images to guide style or composition (image-to-image). It outputs up to 4K across 8 aspect ratios and can return up to 10 images per request. Images can be saved as PNG, JPEG, and WebP. It runs through OpenAI, OpenRouter, Runware, and Replicate using your own API key, from about $0.053 per image.
- Released
- Apr 2026
- Pricing
- $0.053 per image
- Max resolution
- 4K
- Aspect ratios
- 1:1, 3:2, 2:3 +5 more
- Image-to-image
- Up to 16 reference images
- Batch
- Up to 10 per request
- Output formats
- PNG, JPEG, WebP
- Text to image rank
- #3
- Image edit rank
- #4
Samples
Generated with GPT Image 2 via Replicate. The same three prompts run against every model in the catalog, first result kept, so the only thing that changes between two models’ tiles is the model.
Materials, reflections, macro detail
Skin texture, lighting, shallow depth of field
Text rendering, layout, flat colour
OpenAI
OpenAI builds GPT, DALL·E, the Sora family, and the open-weight gpt-oss models, and has been a central force behind the modern wave of generative AI.
openai.com ↗OpenAI's flagship GPT-6 model for complex reasoning, coding, research, and long-running agent work, with vision and a 1M-token context window.
GPT 6 Astra in OpenAI's pro reasoning mode, which works longer on each answer for the highest quality on hard tasks.
OpenAI's life sciences model, with specialized biological reasoning and scientific tool use. Only organizations approved through OpenAI's trusted-access program can call it, for internal research.
OpenAI's cybersecurity model for investigating vulnerabilities, reproducing them in an authorized test environment and verifying fixes. Only organizations approved through OpenAI's Daybreak program can call it.
OpenAI's update to GPT 6 Sol, the cost-efficient high-end GPT-6 tier, for agentic coding and document work, with vision and a 1M-token context window.
OpenAI's fast, efficient GPT-6.1 tier for visual reasoning, computer use and clear writing, improving on GPT 5.6 Terra with a 1M-token context window.
Nine images, four clips, $3.17 in API bills: what ByteDance's Seedream and Seedance actually return on prompts we ran ourselves.
Three tabs, one question, three good answers. So which AI wins? Wrong question. Here's the one to open for each job.
Reasoning came to image generation, native typography stopped being a tell, and the leaderboard turned over twice. The Feb–May 2026 catalog.
A 2026 field guide: what each modality is good at, what it costs, and three ways to chain them together.