GPT Image 2 on AI Gateway

Source: Vercel Blog

Overview

GPT Image 2 is now available on the Vercel AI Gateway.
OpenAI’s newest image model supports detailed instruction following, accurate placement and relationships between objects, and rendering of dense text across multiple aspect ratios.

The model can render fine‑grained elements—including small text, iconography, UI elements, dense compositions, and subtle stylistic constraints—at up to 2K resolution. Non‑English text is also supported and reads coherently.

GPT Image 2 can produce photos, cinematic stills, pixel art, manga, and other distinct visual styles, with consistency in texture, lighting, composition, and detail. This suits workflows such as game prototyping, storyboarding, marketing creative, and medium‑specific asset generation.

Usage

To use GPT Image 2, set the model to openai/gpt-image-2 in the AI SDK, or try it directly in the model playground.

import { generateImage } from 'ai';

const result = await generateImage({
  model: 'openai/gpt-image-2',
  prompt: 'Poster of Vercel AI products, Baohaus style.',
});

Example Images

AI Gateway Features

AI Gateway provides a unified API for:

• Calling models, tracking usage and cost
• Configuring retries, failover, and performance optimizations for higher‑than‑provider uptime
• Built‑in custom reporting and observability
• Bring Your Own Key support
• Intelligent provider routing with automatic retries

Further Reading

• Learn more about AI Gateway
• View the AI Gateway model leaderboard
• Try the model in the model playground