Generate and edit photorealistic images with OpenAI's GPT Image 1 model. No account needed, pay-per-use.
GPT Image 1 is OpenAI's dedicated image generation model, released in March 2025. Unlike DALL·E, it's built on the GPT architecture, enabling superior text rendering, photorealistic output, and natural language image editing. It supports text-to-image generation, image editing with masks (inpainting), transparent backgrounds, and multiple output formats.
GPT Image 1 is priced per token. Typical costs: ~$0.02–$0.07 per image depending on quality and size. Text input: $5/1M tokens. Image input: $10/1M tokens. Image output: $40/1M tokens.
Hero banners, ad creatives, and campaign keyframes with sharp on-image text and consistent brand styling.
Generate or edit product photos with controlled backgrounds, transparent PNGs ready for storefronts and listings.
Vertical and square formats for Instagram, TikTok, and X — generated in seconds with caption-friendly text rendering.
Mask any region and rewrite it: replace objects, remove distractions, or extend a photo beyond its original frame.
Posters, infographics, and quote cards with readable, accurately-spelled text — no manual lettering required.
Iterate on logo directions, color palettes, and brand mood boards using natural-language prompts.
Open the playground above and select gpt-image-1 as your model. New accounts get free credits — no payment required to try.
Describe what you want in plain English or Chinese. Be specific about style, composition, lighting, and any text that should appear in the image.
Click generate for text-to-image, or upload a reference and draw a mask for inpainting. Pick size and quality on the right panel.
Export as PNG (with transparent background option), JPEG, or WebP. All generated images are commercially usable.
| GPT Image 1 | GPT Image 1.5 | |
|---|---|---|
| Speed | Standard | 4× faster |
| Edit fidelity | Good | Preserves details precisely |
| Text rendering | Good | Significantly better |
| Price (output) | $40/1M tokens | $32/1M tokens (20% cheaper) |
| Best for | Standard generation | Production-grade work |
Open the playground above, sign in to claim your free credits, and start creating in under a minute. Your credits also work with GPT Image 1.5 and GPT Image 2 when you want to compare quality.
Your generated image will appear here.
Generated images will appear here.
Quality Comparison (gpt-image-2)
| Quality | Speed | Image Detail | Credits/Image | Best For |
|---|---|---|---|---|
| Low | Fastest (3-8s) | Good composition, less detail | 10 | Quick iterations, bulk generation, social media |
| Medium | Moderate (10-20s) | Rich details, good textures | 40 | Marketing images, presentations |
| High | Slower (20-40s) | Highest fidelity, finest details | 110 | Print, posters, premium assets |
| Auto | Model decides | Auto-selected by model | 40 | When unsure |
Model Comparison
| Model | Highlights | Low/Image | High/Image |
|---|---|---|---|
| gpt-image-2 | Latest, best results | 10 | 110 |
Cost-Saving Tips
Enter a text prompt describing the image you want. Adjust parameters like size (Square, Landscape, Portrait), quality (Low/Medium/High), output format (PNG/JPEG/WebP), and background (Opaque or Transparent). Click "Generate" and GPT Image 2 will create a brand-new image from your description.
Tips for Better GPT Image 2 Results
Upload a source image, write a prompt describing the changes you want, and GPT Image 2 will modify the image accordingly. Without a mask, GPT Image 2 decides which areas to change. With a mask, you can precisely control which regions are modified.
You can use Edit mode for GPT Image 2 image-to-image generation without a mask. Simply upload a reference image and describe the transformation you want in the prompt — for example, "Convert this photo to a watercolor painting" or "Reimagine this scene in a cyberpunk style". GPT Image 2 will use your image as a reference to generate a new version.
Example GPT Image 2 Prompts for Image-to-Image