Getting Started with SUTRA

SUTRA is a family of large multi-lingual language models developed by TWO AI, offering powerful AI capabilities through a simple, OpenAI-compatible API. This guide helps developers quickly integrate SUTRA-V2 for conversational AI, multilingual tasks, and more, from prototyping to production.

Installation

Install the required SDKs for your preferred programming language:

pip install openai
npm install openai
npm install openai react

Getting Your API Key

Sign up to receive free SUTRA API KEY. All API requests require a SUTRA API key. Store your key securely as an environment variable:

export SUTRA_API_KEY="your_api_key_here"

If you are using Google Colab, you can:

  • Click the 🔑 icon in the left sidebar.
  • Add a secret named SUTRA_API_KEY.

API Reference

Base URL

SUTRA API uses an API format compatible with OpenAI. By modifying the configuration, you can also use the OpenAI SDK or softwares compatible with the OpenAI API.

https://api.two.ai/v2

Chat Completions Endpoint

Interact with SUTRA-V2 in a conversational format.

  • Endpoint: /chat/completions
  • Method: POST
  • Required Headers:
    • Authorization: Bearer <YOUR_SUTRA_API_KEY>
    • Content-Type: application/json
  • Optional Headers (Streaming):
    • Accept: text/event-stream

Request Parameters

ParameterTypeRequiredDescription
modelstringYesModel ID (e.g., sutra-v2)
messagesarrayYesArray of message objects with role and content
max_tokensintegerNoMaximum tokens to generate (default: 1024)
temperaturenumberNoControls randomness (0-1, default: 0.7)
streambooleanNoIf true, responses are sent incrementally

Invoke the Chat Completion API

Once you have obtained an API key, you can access the SUTRA API using the example scripts below.
This is a non-stream example—set the stream parameter to true to receive a streaming response.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("SUTRA_API_KEY", "YOUR_SUTRA_API_KEY"),
    base_url="https://api.two.ai/v2"
)

response = client.chat.completions.create(
    model="sutra-v2",
    messages=[{"role": "user", "content": "Tell me about Mars exploration in three sentences."}],
    max_tokens=1024,
    temperature=0.7
)
print(response.choices[0].message.content)
import { OpenAI } from "openai";

async function main() {
  const client = new OpenAI({
    apiKey: process.env.SUTRA_API_KEY || "YOUR_SUTRA_API_KEY",
    baseURL: "https://api.two.ai/v2",
  });

  const response = await client.chat.completions.create({
    model: "sutra-v2",
    messages: [
      {
        role: "user",
        content: "Tell me about Mars exploration in three sentences.",
      },
    ],
    max_tokens: 1024,
    temperature: 0.7,
  });

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

main();
import React, { useState } from "react";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_SUTRA_API_KEY",
  baseURL: "https://api.two.ai/v2",
  dangerouslyAllowBrowser: true, // Note: Use a backend proxy in production
});

function App() {
  const [prompt, setPrompt] = useState("");
  const [response, setResponse] = useState("");

  const handleSubmit = async () => {
    try {
      const result = await client.chat.completions.create({
        model: "sutra-v2",
        messages: [
          {
            role: "user",
            content:
              prompt || "Tell me about Mars exploration in three sentences.",
          },
        ],
        max_tokens: 1024,
        temperature: 0.7,
      });
      setResponse(result.choices[0].message.content);
    } catch (error) {
      setResponse(`Error: ${error.message}`);
    }
  };

  return (
    <div style={{ padding: "20px" }}>
      <input
        type="text"
        value={prompt}
        onChange={(e) => setPrompt(e.target.value)}
        placeholder="Ask SUTRA-V2 about Mars exploration..."
      />
      <button onClick={handleSubmit}>Submit</button>
      <p>{response}</p>
    </div>
  );
}

export default App;

Streaming Responses

Enable real-time output by setting "stream": true and including the Accept: text/event-stream header.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("SUTRA_API_KEY", "YOUR_SUTRA_API_KEY"),
    base_url="https://api.two.ai/v2"
)

stream = client.chat.completions.create(
    model="sutra-v2",
    messages=[{"role": "user", "content": "Write a short story in Hindi about space exploration."}],
    max_tokens=1024,
    temperature=0.7,
    stream=True
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
import { OpenAI } from "openai";

async function streamSutra() {
  const client = new OpenAI({
    apiKey: process.env.SUTRA_API_KEY || "YOUR_SUTRA_API_KEY",
    baseURL: "https://api.two.ai/v2",
  });

  const stream = await client.chat.completions.create({
    model: "sutra-v2",
    messages: [
      {
        role: "user",
        content: "Write a short story in Hindi about space exploration.",
      },
    ],
    max_tokens: 1024,
    temperature: 0.7,
    stream: true,
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || "");
  }
}

streamSutra();
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": "मंगल ग्रह के अन्वेषण के बारे में एक छोटी कहानी लिखें।"}],
        "max_tokens": 1024,
        "temperature": 0.7,
        "stream": true
    }'

Multilingual Capabilities

SUTRA-V2 supports over 50 languages, including Hindi, Bengali, Gujarati, Tamil, Telugu, Japanese, Korean, English, French, German, and more. Simply provide input in any supported language, and SUTRA will respond accordingly.

Example in Hindi

response = client.chat.completions.create(
    model="sutra-v2",
    messages=[{"role": "user", "content": "भारत के अंतरिक्ष कार्यक्रम के बारे में तीन वाक्यों में बताएं।"}],
    max_tokens=1024,
    temperature=0.7
)
print(response.choices[0].message.content)

SUTRA Starter Guide Tutorial

Watch our comprehensive tutorial to quickly get started with SUTRA:

Troubleshooting

  • Invalid API Key: Verify at TWO AI SUTRA API.
  • Model Not Found: Use sutra-v2 for conversations or sutra-r0 for reasoning. SUTRA-V1 was deprecated on March 22, 2025.
  • Rate Limits: Reduce request frequency.
  • Language Issues: Ensure prompts align with the target language’s script and syntax.

Support

Start building with SUTRA to create scalable, multilingual AI applications today!

Introduction to SUTRA

Models Overview

On this page

Installation
Getting Your API Key
API Reference
Base URL
Chat Completions Endpoint
Request Parameters
Invoke the Chat Completion API
Streaming Responses
Multilingual Capabilities
Example in Hindi
SUTRA Starter Guide Tutorial
Troubleshooting
Support