English | हिंदी (Hindi) | 한국어 (Korean) | Español (Spanish)

Overview

SUTRA is a family of large multi-lingual language models (LMLMs) developed by TWO AI. SUTRA's dual-transformer architecture extends the power of both MoE (Mixture of Experts) and Dense AI language model approaches, delivering cost-efficient multilingual capabilities across 50+ languages.

What You'll Find in This Repository

Section	Description
Get Started	Introductory tutorials, basic usage patterns, and setup guides
Multilingual	Code samples showcasing SUTRA's capabilities across 50+ languages
Integration Guides	Instructions for integrating SUTRA with popular frameworks and tools
Chat with Data	Retrieval-Augmented Generation examples for knowledge-intensive tasks
Agent Building	Tutorials on creating conversational agents and assistants
Starter Apps	Ready-to-use application templates to jumpstart your development
Examples	Additional code examples and implementations

Sutra Starter Guide

Get Your API Key

Get your API key by visiting TWO AI's SUTRA API Page.

⚠️ Security Note: Keep your API key secure! Never expose it in client-side code or public repositories.

API Endpoint

https://api.two.ai/v2/chat/completions

Quick Start

Sample Code

cURL

curl -X POST "https://api.two.ai/v2/chat/completions" \
  -H "Authorization: Bearer $SUTRA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept text/event-stream" \
  -d '{
  "model": "sutra-v2",
  "messages": [
    {"role": "user", "content": "मुझे मंगल ग्रह के बारे में 5 पैराग्राफ दीजिए"}
  ]
}'

Python

import os
from openai import OpenAI

url = 'https://api.two.ai/v2'

client = OpenAI(base_url=url,
                api_key=os.environ.get("SUTRA_API_KEY"))

response = client.chat.completions.create(
    model='sutra-v2',
    messages=[{"role": "user", "content": "मुझे मंगल ग्रह के बारे में 5 पैराग्राफ दीजिए"}],
    max_tokens=1024,
    temperature=0
)

print(response.choices[0].message.content)

JavaScript/Node.js

import { OpenAI } from 'openai';

async function testSutra() {
    const url = 'https://api.two.ai/v2';

    const client = new OpenAI({
        apiKey: process.env.SUTRA_API_KEY,
        baseURL: url,
    })

    const response = await client.chat.completions.create(
        {
            model: 'sutra-v2',
            messages: [{ role: 'user', content: 'मुझे मंगल ग्रह के बारे में 5 पैराग्राफ दीजिए' }],
            max_tokens: 1024,
            temperature: 0
        }
    );

    console.log(response.choices[0].message.content);
}

(async () => { 
    await testSutra(); 
    process.exit(0); 
})();

Features

• Multilingual Support: Built-in support for 50+ languages
• OpenAI-compatible API: Easy integration with existing OpenAI-based applications
• Dual-transformer Architecture: Combines the power of MoE and Dense AI approaches
• High Performance: Optimized for various use cases and domains
• Streaming Support: Real-time response streaming capabilities

Resources

• Join our Discord community for real-time support and discussions
• SUTRA Docs here
• Chat with us on Chat with SUTRA
• Follow SUTRA on Twitter for updates

Getting Support

• Visit TWO AI's website for more information
• Contact us: hello@two.ai

Video Tutorial

Contributing

We welcome contributions to the SUTRA Cookbooks repository! To contribute:

1. Fork and clone the repository
2. Create a new branch for your changes
3. Make your changes following our documentation standards
4. Test your examples thoroughly
5. Submit a pull request

For major changes, please open an issue first to discuss your ideas.

Legal

• Privacy Policy
• Terms of Service

---

2025 TWO AI | All Rights Reserved