What is GPT Image 1?

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.

Key Capabilities

Text-to-image generation with accurate text rendering
Image editing and inpainting with mask support
Transparent background export (PNG)
Multiple sizes: 1024×1024, 1536×1024, 1024×1536
Quality tiers: Low, Medium, High
Output formats: PNG, JPEG, WebP

API Pricing

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.

What you can build with GPT Image 1

Marketing visuals

Hero banners, ad creatives, and campaign keyframes with sharp on-image text and consistent brand styling.

E-commerce product shots

Generate or edit product photos with controlled backgrounds, transparent PNGs ready for storefronts and listings.

Social media posts

Vertical and square formats for Instagram, TikTok, and X — generated in seconds with caption-friendly text rendering.

Photo editing & inpainting

Mask any region and rewrite it: replace objects, remove distractions, or extend a photo beyond its original frame.

Text-heavy graphics

Posters, infographics, and quote cards with readable, accurately-spelled text — no manual lettering required.

Logo & branding concepts

Iterate on logo directions, color palettes, and brand mood boards using natural-language prompts.

How to use GPT Image 1

1
Pick GPT Image 1
Open the playground above and select gpt-image-1 as your model. New accounts get free credits — no payment required to try.
2
Write your prompt
Describe what you want in plain English or Chinese. Be specific about style, composition, lighting, and any text that should appear in the image.
3
Generate or edit
Click generate for text-to-image, or upload a reference and draw a mask for inpainting. Pick size and quality on the right panel.
4
Download your image
Export as PNG (with transparent background option), JPEG, or WebP. All generated images are commercially usable.

GPT Image 1 vs GPT Image 1.5

	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

Frequently Asked Questions

Yes. New accounts on imagesv2.ai receive free credits on sign up — enough to fully test text-to-image, editing, and transparent-background export before deciding to top up.

About $0.02–$0.07 per image, depending on size and quality tier. On this site you pay in credits, and the quote is shown before you generate so there are no surprises.

Yes. Upload an image, draw a mask over the region you want to change, and describe the edit in natural language. GPT Image 1 will inpaint that region while leaving the rest of the image intact.

Yes. Export as PNG with transparency enabled — useful for product cutouts, logos, and any asset that needs to sit on a colored background.

Use GPT Image 1.5 for production work — it's 4× faster, 20% cheaper, and preserves edit details more precisely. Use GPT Image 1 if you need a specific behavior of the older snapshot or for cost-comparison testing.

OpenAI's terms grant you ownership of generated outputs, including for commercial use. Avoid prompting for trademarked logos, real public figures, or copyrighted characters to stay on the safe side.

Start generating with GPT Image 1

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.

This generation costs: 10 credits

History

Generated images will appear here.

How to Use the GPT Image 2 Playground

GPT Image 2 Parameter Guide

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

Start with Low quality to iterate on prompts, then switch to Medium or High for the final version.
Credits scale with image count: per-image cost × number of images.
New users get a 3-credit first-trial bonus on the standard tier (one-time).

GPT Image 2 Text-to-Image Generation

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

Be specific and detailed in your prompt — describe lighting, composition, style, and mood.
Use "Transparent" background to get cutout images for product photos, stickers, and design assets.
Low quality is fastest and cheapest; High quality gives the best results but costs more.
Generate multiple GPT Image 2 images (up to 10) to compare different interpretations of your prompt.

GPT Image 2 Image Editing (Inpainting)

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.

How the Mask Editor Works

Upload your source image in Edit mode.
Click "Create Mask" to open the mask editor.
Draw on the image with the brush — the red areas you paint will become the editable regions.
Adjust the brush size slider for fine or coarse control.
Click "Save Mask" to generate the mask file. You'll see a preview (black = keep, transparent = edit).
Write a prompt describing what should appear in the masked areas.
Click "Edit Image" to submit.

GPT Image 2 Image-to-Image (Style Transfer)

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

"Convert this photo to Studio Ghibli anime style"
"Reimagine this scene as a 3D rendered illustration"
"Transform this into a vintage oil painting"
"Make this look like a professional product photo with white background"

Edit Image

Modify an existing image with a text prompt.

History

Generated images will appear here.

How to Use the GPT Image 2 Playground

GPT Image 2 Parameter Guide

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

Start with Low quality to iterate on prompts, then switch to Medium or High for the final version.
Credits scale with image count: per-image cost × number of images.
New users get a 3-credit first-trial bonus on the standard tier (one-time).

GPT Image 2 Text-to-Image Generation

Tips for Better GPT Image 2 Results

Be specific and detailed in your prompt — describe lighting, composition, style, and mood.
Use "Transparent" background to get cutout images for product photos, stickers, and design assets.
Low quality is fastest and cheapest; High quality gives the best results but costs more.
Generate multiple GPT Image 2 images (up to 10) to compare different interpretations of your prompt.

GPT Image 2 Image Editing (Inpainting)

How the Mask Editor Works

Upload your source image in Edit mode.
Click "Create Mask" to open the mask editor.
Draw on the image with the brush — the red areas you paint will become the editable regions.
Adjust the brush size slider for fine or coarse control.
Click "Save Mask" to generate the mask file. You'll see a preview (black = keep, transparent = edit).
Write a prompt describing what should appear in the masked areas.
Click "Edit Image" to submit.

GPT Image 2 Image-to-Image (Style Transfer)

Example GPT Image 2 Prompts for Image-to-Image

"Convert this photo to Studio Ghibli anime style"
"Reimagine this scene as a 3D rendered illustration"
"Transform this into a vintage oil painting"
"Make this look like a professional product photo with white background"

GPT Image 1 — AI Image Generator Online

What you can build with GPT Image 1

Pick GPT Image 1

Write your prompt

Generate or edit

Download your image

Looking for a different tool?

How to Use the GPT Image 2 Playground

How to Use the GPT Image 2 Playground

GPT Image 1 — AI Image Generator Online

What you can build with GPT Image 1

Pick GPT Image 1

Write your prompt

Generate or edit

Download your image

Is GPT Image 1 free to try?

How much does each image cost?

Can I edit an existing image with GPT Image 1?

Does it support transparent backgrounds?

Should I use GPT Image 1 or GPT Image 1.5?

Are the generated images safe for commercial use?

Looking for a different tool?

How to Use the GPT Image 2 Playground

How to Use the GPT Image 2 Playground