# GPT Image 1

OpenAI's image generation model for creating and editing images from text prompts via the API, supporting high-fidelity generation across a wide range of styles and subjects.

- **Model ID:** `openai/gpt-image-1`
- **Type:** image
- **Providers:** openai
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** $5/1M input tokens, $40/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-image-1

## Supported parameters

- **Parameters:** `aspectRatio`, `resolution`
- **Operations:** `text-to-image`, `image-to-image`, `inpainting`
- **Input modalities:** `text`, `image`
- **Output modalities:** `image`
- **Aspect ratios:** `1:1`, `2:3`, `3:2`
- **Resolutions:** `1024x1024`, `1024x1536`, `1536x1024`
- **Durations:** Not reported
- **Frame rates:** Not reported
- **Maximum outputs per request:** Not reported
- **Maximum input images:** Not reported
- **Input image formats:** `png`, `jpeg`, `webp`
- **Maximum input image size:** 50 MB

## Example

```ts
import { experimental_generateImage as generateImage } from 'ai';

const result = await generateImage({
  model: 'openai/gpt-image-1',
  prompt: 'A red balloon on a wooden table.'
});
```

## About

GPT Image 1 was released on March 25, 2025 as OpenAI's image generation model available through the API. It generates images from text descriptions, supporting creation of new images, editing of existing images, and generation of variations.

The model handles a wide range of subjects and styles, from photorealistic scenes to illustrations, diagrams, and abstract art. It accepts detailed text prompts describing the desired output and produces images that match the description with high fidelity.

You can generate custom visuals on demand, create personalized content, and build creative tools without separate image generation infrastructure.

## What to consider

GPT Image 1 is a generation-focused model, not a language model. It produces images from text descriptions rather than text from text. Pricing is per image generated rather than per token.

The model integrates into applications through the images API endpoint, accepting text prompts and returning generated images.

## When to use

### Best For

- **Product imagery:** Generating product photos, mockups, and marketing visuals from descriptions
- **Content creation:** Illustrations, thumbnails, and visual content for blogs and social media
- **Design iteration:** Rapidly exploring visual concepts from text descriptions
- **Custom asset generation:** Creating unique icons, backgrounds, and UI elements programmatically
- **Creative tools:** Building image generation features into creative applications

### Consider Alternatives When

- **Text tasks:** Any GPT model for text generation, analysis, or coding
- **Image understanding:** GPT-4o or GPT-4.1 for analyzing existing images rather than generating new ones
- **Video generation:** Specialized video models for motion content
- **Photo-realistic editing:** Specialized tools for precise photo manipulation

## Best for

- **Product imagery:** Generating product photos, mockups, and marketing visuals from descriptions
- **Content creation:** Illustrations, thumbnails, and visual content for blogs and social media
- **Design iteration:** Rapidly exploring visual concepts from text descriptions
- **Custom asset generation:** Creating unique icons, backgrounds, and UI elements programmatically
- **Creative tools:** Building image generation features into creative applications

## Consider alternatives

- **Text tasks:** Any GPT model for text generation, analysis, or coding
- **Image understanding:** GPT-4o or GPT-4.1 for analyzing existing images rather than generating new ones
- **Video generation:** Specialized video models for motion content
- **Photo-realistic editing:** Specialized tools for precise photo manipulation

## Frequently asked questions

### What can GPT Image 1 generate?

It creates images from text descriptions, supporting a wide range of subjects, styles, and compositions including photorealistic scenes, illustrations, diagrams, and artistic styles.

### Can GPT Image 1 edit existing images?

Yes. It supports image editing operations where you provide an existing image and describe the changes you want.

### How is GPT Image 1 priced?

Pricing is per image generated, with costs varying by resolution and quality settings. Check the pricing section of this page for current rates.

### Can I control the output resolution?

Yes. The API accepts resolution and quality parameters that control the output characteristics.

### How does AI Gateway handle authentication for GPT Image 1?

AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.

### What are typical generation times?

This page shows live performance metrics measured across real AI Gateway traffic.

## Links

- [Model page](https://vercel.com/ai-gateway/models/gpt-image-1)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://platform.openai.com/docs/models/gpt-image-1)
- [Provider pricing](https://platform.openai.com/docs/pricing#image-generation)


If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.