# GPT Image 1.5

The successor to gpt-image-1, delivering improved visual quality, better text rendering, and more faithful prompt interpretation.

- **Model ID:** `openai/gpt-image-1.5`
- **Type:** image
- **Providers:** openai
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** $5/1M input tokens, $32/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-image-1.5

## Supported parameters

- **Parameters:** `aspectRatio`, `resolution`, `n`
- **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:** 10
- **Maximum input images:** 16
- **Input image formats:** `png`, `webp`, `jpg`
- **Maximum input image size:** 50 MB

## Example

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

const result = await generateImage({
  model: 'openai/gpt-image-1.5',
  prompt: 'A red balloon on a wooden table.'
});
```

## About

GPT Image 1.5 was released on December 16, 2025 as the successor to gpt-image-1 in OpenAI's image generation lineup. Building on gpt-image-1, it delivers improvements in visual fidelity, text rendering within images, and the model's ability to faithfully interpret complex, multi-element prompts.

Text rendering has been a persistent challenge for image generation models. GPT Image 1.5 improves this substantially, producing more legible and accurate text within generated images. This opens up use cases that require readable text overlays, signs, labels, and other textual elements in visual content.

The model also shows better compositional understanding, handling complex prompts with multiple subjects, specific spatial relationships, and detailed style instructions more accurately. For applications where visual quality and prompt fidelity are critical, it provides a meaningful step up over gpt-image-1.

## What to consider

GPT Image 1.5 improves on gpt-image-1 across key dimensions including visual fidelity, text rendering within images, and accuracy of complex prompt interpretation.

For projects requiring image generation with better text rendering and prompt fidelity, GPT Image 1.5 is a step up from gpt-image-1.

## When to use

### Best For

- **Text-in-image applications:** Generating images with accurate, readable text overlays
- **Professional visual content:** Marketing materials, product imagery, and branded content requiring high fidelity
- **Complex scene composition:** Detailed scenes with multiple elements, specific spatial relationships, and nuanced descriptions
- **Design mockups:** High-quality visual prototypes from detailed specifications
- **Premium creative tools:** Applications where image quality is a key differentiator

### Consider Alternatives When

- **Cost-sensitive generation:** gpt-image-1-mini for high-volume use at lower cost
- **Image analysis:** GPT-4o or GPT-4.1 for understanding existing images
- **Batch generation:** gpt-image-1 or mini for high-volume pipelines where gpt-image-1 quality is sufficient
- **Text tasks:** Any GPT model is the better fit for non-image workloads like analysis, coding, or generation

## Best for

- **Text-in-image applications:** Generating images with accurate, readable text overlays
- **Professional visual content:** Marketing materials, product imagery, and branded content requiring high fidelity
- **Complex scene composition:** Detailed scenes with multiple elements, specific spatial relationships, and nuanced descriptions
- **Design mockups:** High-quality visual prototypes from detailed specifications
- **Premium creative tools:** Applications where image quality is a key differentiator

## Consider alternatives

- **Cost-sensitive generation:** gpt-image-1-mini for high-volume use at lower cost
- **Image analysis:** GPT-4o or GPT-4.1 for understanding existing images
- **Batch generation:** gpt-image-1 or mini for high-volume pipelines where gpt-image-1 quality is sufficient
- **Text tasks:** Any GPT model is the better fit for non-image workloads like analysis, coding, or generation

## Frequently asked questions

### What improved in GPT Image 1.5 over gpt-image-1?

Key improvements include better visual fidelity, more accurate text rendering within images, and more faithful interpretation of complex multi-element prompts.

### Can GPT Image 1.5 render text in images?

Yes, with substantially improved accuracy over previous versions. Text overlays, signs, labels, and other textual elements are rendered more legibly.

### How is GPT Image 1.5 priced?

Pricing is per image generated. Check the pricing section of this page for current rates at different resolution and quality settings.

### How does AI Gateway handle authentication for GPT Image 1.5?

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.

### Should I use this instead of gpt-image-1?

For new projects and applications where image quality is important, yes. For existing high-volume pipelines where the quality of gpt-image-1 is sufficient, upgrading is optional.

### 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-1.5)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://platform.openai.com/docs/models/gpt-image-1.5)
- [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.