openapi: 3.1.0
info:
  title: SambaCloud API
  description: |
    SambaCloud is SambaNova's managed inference API for open-source models
    (DeepSeek, Llama, Gemma, MiniMax, gpt-oss). The HTTP surface is
    OpenAI-compatible: chat completions, completions, embeddings, and
    model listing endpoints all match the OpenAI shape so existing OpenAI
    clients can be pointed at `https://api.sambanova.ai/v1` by changing
    base URL and API key.
  version: "2026-05-23"
  contact:
    name: SambaNova
    url: https://docs.sambanova.ai
servers:
  - url: https://api.sambanova.ai/v1
    description: SambaCloud production
security:
  - bearerAuth: []
paths:
  /chat/completions:
    post:
      summary: Create a chat completion
      description: |
        OpenAI-compatible chat completions endpoint. Accepts a list of
        messages and returns a model completion. Supports streaming via
        `stream: true` with `text/event-stream` responses.
      operationId: createChatCompletion
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: Chat completion result (or SSE stream when streaming).
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
            text/event-stream:
              schema:
                type: string
                description: Server-Sent Events stream of completion chunks.
        '400':
          description: Invalid request
        '401':
          description: Missing or invalid API key
        '429':
          description: Rate limited
  /completions:
    post:
      summary: Create a text completion
      description: OpenAI-compatible text completions endpoint.
      operationId: createCompletion
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - prompt
              properties:
                model:
                  type: string
                prompt:
                  oneOf:
                    - type: string
                    - type: array
                      items:
                        type: string
                max_tokens:
                  type: integer
                temperature:
                  type: number
                top_p:
                  type: number
                stream:
                  type: boolean
                stop:
                  oneOf:
                    - type: string
                    - type: array
                      items:
                        type: string
      responses:
        '200':
          description: Text completion result
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
  /embeddings:
    post:
      summary: Create embeddings
      description: OpenAI-compatible embeddings endpoint for supported models.
      operationId: createEmbeddings
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - input
              properties:
                model:
                  type: string
                input:
                  oneOf:
                    - type: string
                    - type: array
                      items:
                        type: string
                encoding_format:
                  type: string
                  enum: [float, base64]
      responses:
        '200':
          description: Embeddings response
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
  /models:
    get:
      summary: List models
      description: Lists models currently available on SambaCloud.
      operationId: listModels
      responses:
        '200':
          description: Model list
          content:
            application/json:
              schema:
                type: object
                properties:
                  object:
                    type: string
                    example: list
                  data:
                    type: array
                    items:
                      $ref: '#/components/schemas/Model'
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: |
        SambaCloud API key issued from the /apis dashboard on
        cloud.sambanova.ai, sent as `Authorization: Bearer <key>`.
  schemas:
    Model:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: model
        created:
          type: integer
        owned_by:
          type: string
    ChatMessage:
      type: object
      required:
        - role
        - content
      properties:
        role:
          type: string
          enum: [system, user, assistant, tool]
        content:
          oneOf:
            - type: string
            - type: array
              items:
                type: object
                additionalProperties: true
        name:
          type: string
        tool_call_id:
          type: string
    ChatCompletionRequest:
      type: object
      required:
        - model
        - messages
      properties:
        model:
          type: string
          description: |
            Model identifier such as DeepSeek-V3.1, Llama-3.3-70B-Instruct,
            Llama-4-Maverick-17B-128E-Instruct, or gpt-oss-120b.
        messages:
          type: array
          items:
            $ref: '#/components/schemas/ChatMessage'
        temperature:
          type: number
        top_p:
          type: number
        max_tokens:
          type: integer
        stream:
          type: boolean
        stop:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
        tools:
          type: array
          items:
            type: object
            additionalProperties: true
        tool_choice:
          oneOf:
            - type: string
            - type: object
              additionalProperties: true
        response_format:
          type: object
          additionalProperties: true
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: chat.completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              message:
                $ref: '#/components/schemas/ChatMessage'
              finish_reason:
                type: string
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
            completion_tokens:
              type: integer
            total_tokens:
              type: integer