Command Palette
Search for a command to run...
openai/gpt-image-2GPT Image 2 image generation API by OpenAI — up to 4K with native reasoning, multilingual text rendering, and reference-guided editing.
A detailed scientific infographic of an integrated biohybrid artificial photosynthesis platform for solar-to-fuel conversion, with labeled cross-section diagrams, molecular structures, efficiency charts, and process flow annotations
A photorealistic candid shot of a young man in a light grey Covernat hoodie sitting at station 139 in a premium PC cafe, focused on his laptop screen, soft window light mixing with monitor glow, shallow depth of field
A pixel-perfect recreation of the YouTube homepage UI with a left sidebar showing Home, Shorts, Subscriptions, History, and Explore sections, a top navigation bar with search and profile icon, category filter chips, and an 8-video thumbnail grid with realistic titles, channel names, view counts, and duration stamps
GPT Image 2 is OpenAI's flagship image generation model, released in April 2026. It's one of the first image models with built-in reasoning — the model plans composition and verifies prompt constraints before generating. It supports multilingual text rendering across scripts including CJK, Hindi, and Bengali, making it well-suited for global creative work. It supports up to 4K output and is accessible through the GPT Image 2 API.
Product photography with accurate lighting and materials. Campaign and editorial visuals where photorealism and fine detail matter. Infographics, UI mockups, and poster designs that require legible embedded text. Reference-guided editing — upload up to 4 images to steer style, color palette, or composition.
All parameters are passed in the input object of the run request.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image to generate (1–4000 chars) |
| aspect_ratio | No | Output aspect ratio. Default 1:1. Options: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
| resolution | No | Output resolution. Default 1K. Options: 1K, 2K, 4K (4K only with 16:9, 9:16, or 21:9) |
| image_urls | No | Up to 4 reference images (max 4 MB each) for image-to-image generation |
GPT Image 2 responds well to physical descriptions. "Matte ceramic vase on a walnut table, soft window light from the left" consistently outperforms "a vase on a table."
4K output is restricted to 16:9, 9:16, and 21:9. For maximum detail in landscape or ultra-wide compositions, combine resolution: "4K" with one of these ratios.
Provide reference images that closely match your target style — the model uses them to guide color palette and composition rather than extrapolating from distant references.
Ten options: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9. The default is 1:1.
Yes — 1K, 2K, and 4K are available. 4K is limited to 16:9, 9:16, and 21:9 ratios.
Yes. Upload up to 4 reference images via image_urls to guide the generation with your own visuals.
GPT Image 2 is OpenAI's flagship with built-in reasoning - it plans composition and verifies prompt constraints before generating - and strong multilingual text rendering including CJK. Nano Banana Pro is Google's highest-fidelity model on Gemini 3 Pro, with 4K output, 11 aspect ratios, and up to 8 reference images. Choose GPT Image 2 for reasoning-driven composition and multilingual text; choose Nano Banana Pro for 4K via API and reference-guided editing with more images.
GPT Image 2 is the newer flagship with built-in reasoning and improved multilingual text rendering. GPT Image 1.5 is the prior generation - capable but without the planning/verification step. Choose GPT Image 2 for complex prompts that benefit from reasoning; GPT Image 1.5 suits simpler generation where reasoning overhead is not needed.
Two ways on Runbase: use the Playground at the top of this page to generate instantly with a prompt and optional reference images, or call the API by POSTing to /api/v1/runs with model: "openai/gpt-image-2" and an input object containing prompt (required), aspect_ratio, resolution, and up to 4 image_urls. New accounts receive free credit on signup to try it. See the API tab for full code samples.
GPT Image 2 is priced per generated image across three resolution tiers: 1K (cheapest), 2K, and 4K (highest). See the Pricing section above for current per-image rates.
It is pay-as-you-go rather than free, but new Runbase accounts receive free credit on signup that works toward GPT Image 2 and other models. Once the credit is used up, you pay per generation at the rates shown in the Pricing section.