GPT Image 2 is LIVE Now. Try in Image Generator→
Sign In
Home/Explore/OpenAI Models/openai/gpt-image-2/text-to-image

OpenAI GPT Image 2 Text-to-Image

openai /

OpenAI's GPT Image 2 Text-to-Image generates high-quality images from natural-language prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-image
Input
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

Your request will cost $0.1 per run.

For $1 you can run this model approximately 10 times.

One more thing:

ExamplesView all

Generate an image:A realistic YouTube screenshot showing the official launchpromotional videofor GPT Image V2from OpenAl's official account,with comments,3：2 aspect ratio,4K resolution.
Vincent van Gogh style oil painting, side profile portrait of a man, double exposure composition, inside the silhouette a surreal landscape with swirling starry night sky, glowing stars, sunflowers and wheat field, a painter painting on canvas, small town by the lake with reflections, thick expressive brush strokes, post-impressionism style, vintage art poster design, textured paper background, warm yellow and deep blue contrast, highly detailed, artistic and emotional, high resolution

README

OpenAI GPT Image 2 Text-to-Image

GPT Image 2 Text-to-Image is OpenAI's next-generation AI image generation model that transforms natural-language prompts into high-quality images.

Parameters

ParameterRequiredDescription
promptYesText description of the desired image
aspect_ratioNoAspect ratio: 1:1 (default), 2:3, 3:2

How to Use

  1. Write your prompt — describe the image in detail, including style, lighting, and composition.
  2. Choose aspect ratio (optional) — 1:1 (default), 2:3, or 3:2.
  3. Run — submit and download your generated image.

Notes

  • Prompt is the only required field.
  • Supported aspect ratios: 1:1, 2:3, 3:2.