🤖 GPT Image 1.5 API in JavaScript — Quick Start Guide 2026

Introduction

GPT Image 1.5 is OpenAI's latest and most capable image generation model, released in 2026. Building on the success of DALL-E 3 and GPT Image 1, version 1.5 delivers significantly improved prompt adherence, more realistic textures, better text rendering within images, and enhanced compositional accuracy. It's particularly strong at generating images that match complex, multi-element prompts with high fidelity.

The model supports multiple output formats (standard, HD), various aspect ratios, and can generate up to 10 images in a single API call. It also supports image editing (inpainting) and image variation generation, making it a versatile choice for creative applications.

Through NexaAPI on RapidAPI, you can access GPT Image 1.5 at just $0.02 per image — that's 5x cheaperthan OpenAI's official pricing of $0.10/image. Same model, same quality, dramatically lower cost.

Prerequisites

• Node.js 18+ (native fetch support included)
• npm or yarn package manager
• A free RapidAPI account
• Basic JavaScript or TypeScript knowledge

Installation & Setup

No SDK required — GPT Image 1.5 API works with native fetch. Set up your project:

mkdir gpt-image-app && cd gpt-image-app
npm init -y

# TypeScript (optional):
npm install -D typescript @types/node ts-node

# Create .env file:
echo "RAPIDAPI_KEY=your_key_here" > .env

Subscribe to the GPT Image 1.5 API on RapidAPI to get your API key. The free tier includes enough credits to test your integration.

Quick Start — Generate Your First Image

Here's a minimal working example to generate an image with GPT Image 1.5:

// generate.js
require('dotenv').config();

const generateImage = async (prompt) => {
  const response = await fetch(
    'https://gpt-image-1-5.p.rapidapi.com/generate',
    {
      method: 'POST',
      headers: {
        'x-rapidapi-key': process.env.RAPIDAPI_KEY,
        'x-rapidapi-host': 'gpt-image-1-5.p.rapidapi.com',
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({
        prompt,
        size: '1024x1024',
        quality: 'standard',
        n: 1
      })
    }
  );

  if (!response.ok) {
    throw new Error(`API error: ${response.status} ${response.statusText}`);
  }

  const data = await response.json();
  return data.data[0].url;
};

// Generate an image
generateImage('A futuristic city skyline at night with neon lights and flying cars')
  .then(url => console.log('Image URL:', url))
  .catch(console.error);

TypeScript — Production-Ready Client

For production applications, use this typed client with error handling, retries, and environment variable management:

// gpt-image-client.ts
interface GenerateOptions {
  prompt: string;
  size?: '256x256' | '512x512' | '1024x1024' | '1792x1024' | '1024x1792';
  quality?: 'standard' | 'hd';
  style?: 'vivid' | 'natural';
  n?: number; // 1-10 images
}

interface GenerateResult {
  urls: string[];
  revisedPrompt?: string;
}

class GptImageClient {
  private apiKey: string;
  private host = 'gpt-image-1-5.p.rapidapi.com';

  constructor(apiKey: string) {
    this.apiKey = apiKey;
  }

  async generate(options: GenerateOptions): Promise<GenerateResult> {
    const { prompt, size = '1024x1024', quality = 'standard', style = 'vivid', n = 1 } = options;

    const response = await fetch(`https://${this.host}/generate`, {
      method: 'POST',
      headers: {
        'x-rapidapi-key': this.apiKey,
        'x-rapidapi-host': this.host,
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({ prompt, size, quality, style, n })
    });

    if (!response.ok) {
      const error = await response.json().catch(() => ({}));
      throw new Error(`GPT Image API error ${response.status}: ${error.message || 'Unknown error'}`);
    }

    const data = await response.json();
    return {
      urls: data.data.map((item: { url: string }) => item.url),
      revisedPrompt: data.data[0]?.revised_prompt
    };
  }

  async generateHD(prompt: string): Promise<string> {
    const result = await this.generate({ prompt, quality: 'hd', size: '1024x1024' });
    return result.urls[0];
  }
}

// Usage
const client = new GptImageClient(process.env.RAPIDAPI_KEY!);

const result = await client.generate({
  prompt: 'A serene Japanese garden with cherry blossoms, koi pond, and wooden bridge',
  quality: 'hd',
  size: '1792x1024',
  style: 'natural'
});

console.log('Generated images:', result.urls);
console.log('Revised prompt:', result.revisedPrompt);

Image Editing (Inpainting)

GPT Image 1.5 supports inpainting — editing specific regions of an existing image using a mask:

// inpaint.ts
import * as fs from 'fs';

const editImage = async (
  imageBuffer: Buffer,
  maskBuffer: Buffer,
  prompt: string
) => {
  const formData = new FormData();
  formData.append('image', new Blob([imageBuffer], { type: 'image/png' }), 'image.png');
  formData.append('mask', new Blob([maskBuffer], { type: 'image/png' }), 'mask.png');
  formData.append('prompt', prompt);
  formData.append('size', '1024x1024');

  const response = await fetch('https://gpt-image-1-5.p.rapidapi.com/edit', {
    method: 'POST',
    headers: {
      'x-rapidapi-key': process.env.RAPIDAPI_KEY!,
      'x-rapidapi-host': 'gpt-image-1-5.p.rapidapi.com'
    },
    body: formData
  });

  const data = await response.json();
  return data.data[0].url;
};

// Edit: replace background with a mountain scene
const image = fs.readFileSync('portrait.png');
const mask = fs.readFileSync('background-mask.png'); // white = edit area
const editedUrl = await editImage(image, mask, 'mountain landscape with snow peaks');

Pricing Comparison

NexaAPI offers significant savings on GPT Image 1.5 API access compared to going directly through OpenAI:

💰 Save 5-10x with NexaAPI — same GPT Image 1.5 quality, pay as you go, no monthly commitment.

Frequently Asked Questions