SUTRA (Two AI)

SUTRA is a family of multilingual large language models from Two AI (Numeric), fluent in 50+ languages including Hindi, Gujarati, Tamil, Bengali, Korean, Arabic, and Japanese. The SUTRA API is OpenAI-compatible and serves the SUTRA-V2 instruction/conversation model and the SUTRA-R0 reasoning model through a single Bearer-authenticated REST interface.

3 APIs 0 Features

AILLMMultilingualInferenceReasoning

APIs

SUTRA Chat Completions (Multilingual) API

OpenAI-compatible chat completions powered by SUTRA-V2 across 50+ languages, with streaming (SSE), temperature, max_tokens, and presence_penalty controls for conversational and ...

SUTRA Reasoning API

Advanced multi-step reasoning with the SUTRA-R0 model, surfaced through the same OpenAI-compatible chat completions endpoint for structured problem-solving and deep contextual a...

SUTRA Models API

Lists the SUTRA models available to an account (e.g. sutra-v2, sutra-r0) via the OpenAI-compatible models endpoint.

Collections

SUTRA API

OPEN

Pricing Plans

Sutra Ai Plans Pricing

3 plans

PLANS

Rate Limits

Sutra Ai Rate Limits

3 limits

RATE LIMITS

FinOps

Sutra Ai Finops

FINOPS

Event Specifications

SUTRA Chat Completions Streaming (HTTP + SSE)

AsyncAPI 2.6 description of SUTRA's **chat completion streaming** surface. Two AI (Numeric) does not publish a WebSocket API for SUTRA. The only asynchronous / event-style trans...

ASYNCAPI

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: SUTRA API
  version: '2.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create a chat completion (SUTRA-V2 multilingual)
      type: http
    http:
      method: POST
      url: https://api.two.ai/v2/chat/completions
      headers:
      - name: Content-Type
        value: application/json
      - name: Accept
        value: application/json
      body:
        type: json
        data: "{\n  \"model\": \"sutra-v2\",\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"आर्टिफिशियल इंटेलिजेंस\
          \ क्या है?\" }\n  ],\n  \"max_tokens\": 1024,\n  \"temperature\": 0.7,\n  \"stream\": false\n}"
    docs: 'Generates a model response using SUTRA-V2 across 50+ languages. Set stream to true and Accept: text/event-stream
      for Server-Sent Events.'
  - info:
      name: Create a chat completion (SUTRA-R0 reasoning)
      type: http
    http:
      method: POST
      url: https://api.two.ai/v2/chat/completions
      headers:
      - name: Content-Type
        value: application/json
      - name: Accept
        value: application/json
      body:
        type: json
        data: "{\n  \"model\": \"sutra-r0\",\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"If Alice is taller\
          \ than Bob, and Bob is taller than Carol, who is the tallest?\" }\n  ],\n  \"max_tokens\": 512,\n  \"temperature\"\
          : 0.3,\n  \"presence_penalty\": 0.6\n}"
    docs: Structured multi-step reasoning using the SUTRA-R0 model via the same chat completions endpoint.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List models
      type: http
    http:
      method: GET
      url: https://api.two.ai/v2/models
      headers:
      - name: Accept
        value: application/json
    docs: Lists the SUTRA models currently available to the account (OpenAI-compatible list shape).