SUTRA Chat Completions (Multilingual) API

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