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 analysis.
OpenAPI Specification
openapi: 3.0.1
info:
title: SUTRA API
description: >-
OpenAI-compatible REST API for the SUTRA family of multilingual large
language models from Two AI (Numeric). The SUTRA-V2 model handles
instruction-following and conversational tasks across 50+ languages, and
the SUTRA-R0 model provides advanced multi-step reasoning. The same
chat/completions endpoint serves both models. The documented base URL is
https://api.numeric.tech/v2 and is also reachable as https://api.two.ai/v2;
the OpenAI SDK can be pointed at this base_url directly.
termsOfService: https://www.two.ai
contact:
name: Two AI (Numeric)
url: https://docs.two.ai/docs
version: '2.0'
servers:
- url: https://api.two.ai/v2
description: SUTRA API (two.ai)
- url: https://api.numeric.tech/v2
description: SUTRA API (documented Numeric host)
security:
- bearerAuth: []
tags:
- name: Chat
description: OpenAI-compatible chat completions across SUTRA models.
- name: Models
description: List available SUTRA models.
paths:
/chat/completions:
post:
operationId: createChatCompletion
tags:
- Chat
summary: Create a chat completion
description: >-
Generates a model response for the given conversation. Compatible with
the OpenAI Chat Completions specification. Set model to a SUTRA model
such as sutra-v2 (multilingual instruction/conversation) or sutra-r0
(reasoning). Set stream to true to receive incremental Server-Sent
Events; include the Accept: text/event-stream header when streaming.
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateChatCompletionRequest'
examples:
multilingual:
summary: Multilingual chat with SUTRA-V2
value:
model: sutra-v2
messages:
- role: user
content: आर्टिफिशियल इंटेलिजेंस क्या है?
max_tokens: 1024
temperature: 0.7
reasoning:
summary: Structured reasoning with SUTRA-R0
value:
model: sutra-r0
messages:
- role: user
content: >-
If Alice is taller than Bob, and Bob is taller than
Carol, who is the tallest?
max_tokens: 512
temperature: 0.3
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/CreateChatCompletionResponse'
text/event-stream:
schema:
$ref: '#/components/schemas/ChatCompletionChunk'
'401':
description: Unauthorized - missing or invalid API key.
'429':
description: Too Many Requests - rate limit exceeded.
/models:
get:
operationId: listModels
tags:
- Models
summary: List models
description: >-
Lists the SUTRA models currently available to the authenticated
account, following the OpenAI models list shape.
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/ListModelsResponse'
'401':
description: Unauthorized - missing or invalid API key.
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
Provide your SUTRA API key as a Bearer token in the Authorization
header - Authorization: Bearer <YOUR_SUTRA_API_KEY>.
schemas:
CreateChatCompletionRequest:
type: object
required:
- model
- messages
properties:
model:
type: string
description: SUTRA model ID (e.g. sutra-v2, sutra-r0).
example: sutra-v2
messages:
type: array
description: A list of messages comprising the conversation so far.
items:
$ref: '#/components/schemas/ChatMessage'
max_tokens:
type: integer
description: Maximum number of tokens to generate.
default: 1024
temperature:
type: number
format: float
description: Sampling temperature between 0 and 1.
default: 0.7
stream:
type: boolean
description: >-
If true, partial message deltas are sent as Server-Sent Events.
default: false
presence_penalty:
type: number
format: float
description: >-
Penalizes new tokens based on whether they appear in the text so
far, reducing repetition.
ChatMessage:
type: object
required:
- role
- content
properties:
role:
type: string
enum:
- system
- user
- assistant
description: The role of the message author.
content:
type: string
description: The contents of the message.
CreateChatCompletionResponse:
type: object
properties:
id:
type: string
object:
type: string
example: chat.completion
created:
type: integer
format: int64
model:
type: string
example: sutra-v2
choices:
type: array
items:
$ref: '#/components/schemas/ChatCompletionChoice'
usage:
$ref: '#/components/schemas/Usage'
ChatCompletionChoice:
type: object
properties:
index:
type: integer
message:
$ref: '#/components/schemas/ChatMessage'
finish_reason:
type: string
example: stop
ChatCompletionChunk:
type: object
description: A streamed chunk of a chat completion (Server-Sent Events).
properties:
id:
type: string
object:
type: string
example: chat.completion.chunk
created:
type: integer
format: int64
model:
type: string
choices:
type: array
items:
type: object
properties:
index:
type: integer
delta:
$ref: '#/components/schemas/ChatMessage'
finish_reason:
type: string
nullable: true
Usage:
type: object
properties:
prompt_tokens:
type: integer
completion_tokens:
type: integer
total_tokens:
type: integer
ListModelsResponse:
type: object
properties:
object:
type: string
example: list
data:
type: array
items:
$ref: '#/components/schemas/Model'
Model:
type: object
properties:
id:
type: string
example: sutra-v2
object:
type: string
example: model
created:
type: integer
format: int64
owned_by:
type: string
example: two-ai