AI API Examples 🚀

Complete, working code examples for accessing 200+ AI models through a single API.

What is this?

This repository contains ready-to-use examples for calling various AI models (DeepSeek, Qwen, Llama, etc.) through AI Token Hub - a unified API gateway that gives you access to 200+ models with a single API key.

Quick Start

pip install openai

import openai

client = openai.OpenAI(
    base_url="https://1d1aa683c7fe1260-115-190-127-67.serveousercontent.com/v1",
    api_key="YOUR_API_KEY"  # Get from https://aitoken-hub.github.io/aitoken-hub/
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Examples

File	Description	Models
chat/	Basic chat completions	All models
coding/	Code generation & review	DeepSeek-V3, Qwen3
reasoning/	Chain-of-thought reasoning	DeepSeek-R1
vision/	Image understanding	Qwen2.5-VL
batch/	Batch processing patterns	All models
streaming/	Real-time streaming	All models
multilingual/	Translation & multilingual	Qwen3, DeepSeek

Why use these examples?

• ✅ All examples use OpenAI SDK (most developers already know it)
• ✅ Copy-paste ready - just add your API key
• ✅ Covers common patterns: chat, code, reasoning, vision, streaming
• ✅ Works with 200+ models - just change the model name

Available Models

• DeepSeek-V3 (671B) - Best for coding and general tasks
• DeepSeek-R1 (671B) - Advanced reasoning and math
• Qwen3-235B - Alibaba's flagship, great for multilingual
• Qwen3-32B - Fast and cost-effective
• Llama 3.1 405B - Meta's open model
• 90+ more specialized models

Get Your API Key

1. Register at AI Token Hub
2. Get your API key from dashboard
3. Start using any model

License

MIT