GPT-5.2, Sora 2, Veo 3.1 & GPT Image 1.5 API Tutorial — All in One SDK (2026)

Introduction

2026 is the year of multimodal AI. GPT-5.2, GPT Image 1.5, Sora 2, and Veo 3.1 are dominating developer searches — but accessing each requires separate accounts, separate billing, and separate SDKs. NexaAPI solves this.

With a single pip install nexaapi, you get unified access to all four of these trending 2026 AI models — plus 50+ others — at a fraction of the cost of going directly to OpenAI or Google.

Quick Comparison: All 4 Models

Model 1: GPT-5.2 API — Advanced Text & Reasoning

GPT-5.2 features a 400K context window and is designed for autonomous agent workflows. It excels at code generation, long-form content, and complex reasoning tasks.

Python Example

# pip install nexaapi
from nexaapi import NexaAPI

client = NexaAPI(api_key='YOUR_API_KEY')

response = client.chat.completions.create(
    model='gpt-5.2',
    messages=[{'role': 'user', 'content': 'Explain quantum computing in simple terms'}]
)
print(response.choices[0].message.content)

JavaScript Example

// npm install nexaapi
import NexaAPI from 'nexaapi';

const client = new NexaAPI({ apiKey: 'YOUR_API_KEY' });

const text = await client.chat.completions.create({
  model: 'gpt-5.2',
  messages: [{ role: 'user', content: 'Write a product description for a smartwatch' }]
});
console.log(text.choices[0].message.content);

Model 2: GPT Image 1.5 API — Next-Gen Image Generation

GPT Image 1.5 delivers photorealistic outputs at 1024x1024 resolution with precise prompt adherence. At $0.003/image via NexaAPI, it's the most cost-effective option for production image generation.

Python Example

image = client.images.generate(
    model='gpt-image-1.5',
    prompt='A futuristic cityscape at sunset, photorealistic, 8K quality',
    size='1024x1024'
)
print(image.data[0].url)

Model 3: Sora 2 API — AI Video Generation

Sora 2 creates high-quality short video clips from text prompts. Perfect for marketing automation, social media content, and product demonstrations.

Python Example

video = client.videos.generate(
    model='sora-2',
    prompt='A timelapse of a blooming flower in a garden, cinematic quality',
    duration=5
)
print(video.data[0].url)

Model 4: Veo 3.1 API — Cinematic Video Generation

Veo 3.1 from Google DeepMind delivers cinematic-quality video at 1080p. Ideal for brand films, product campaigns, and high-quality content marketing.

Python Example

video2 = client.videos.generate(
    model='veo-3.1',
    prompt='Aerial drone shot of a mountain range at golden hour, cinematic 4K',
    duration=8,
    resolution='1080p'
)
print(video2.data[0].url)

Complete Multimodal Pipeline: All 4 Models

Here's a complete pipeline that uses all four models to generate a full content package for any topic:

from nexaapi import NexaAPI

client = NexaAPI(api_key='YOUR_API_KEY')

def run_all_2026_models(topic: str):
    # GPT-5.2 — Text
    text = client.chat.completions.create(
        model='gpt-5.2',
        messages=[{'role': 'user', 'content': f'Write a tagline for: {topic}'}]
    ).choices[0].message.content
    
    # GPT Image 1.5 — Image
    img = client.images.generate(
        model='gpt-image-1.5',
        prompt=f'Professional photo of {topic}, white background',
        size='1024x1024'
    ).data[0].url
    
    # Sora 2 — Short Video
    vid = client.videos.generate(
        model='sora-2',
        prompt=f'5-second promo clip for {topic}',
        duration=5
    ).data[0].url
    
    # Veo 3.1 — Cinematic
    cine = client.videos.generate(
        model='veo-3.1',
        prompt=f'Cinematic brand film for {topic}',
        duration=8, resolution='1080p'
    ).data[0].url
    
    return {'text': text, 'image': img, 'video': vid, 'cinematic': cine}

results = run_all_2026_models('AI-powered smartwatch')
print(results)

Getting Started