Simplismart Chat Completion API

openapi: 3.1.0
info:
  title: DeepSeek R1 Distil Qwen-32B Chat Completion API
  description: High-capacity LLM for complex tasks
  version: 1.0.0
servers:
- url: https://api.simplismart.live
  description: DeepSeek-R1-Distill-Qwen-32B Proxy Server
security:
- BearerAuth: []
tags:
- name: Chat Completion
  description: Large Language Model chat completion services
paths:
  /chat/completions:
    post:
      tags:
      - Chat Completion
      summary: Create chat completion with Llama 70B
      description: Create a chat completion for given messages with streaming support
      operationId: createChatCompletion70B
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                messages:
                  type: array
                  description: Array of messages in the conversation
                  items:
                    type: object
                    properties:
                      role:
                        type: string
                        enum:
                        - system
                        - user
                        - assistant
                        description: The role of the message sender
                      content:
                        type: string
                        description: The content of the message
                    required:
                    - role
                    - content
                model:
                  type: string
                  description: Model identifier
                  enum:
                  - RedHatAI/DeepSeek-R1-Distill-Qwen-32B-FP8-dynamic
                  default: RedHatAI/DeepSeek-R1-Distill-Qwen-32B-FP8-dynamic
                stream:
                  type: boolean
                  description: Whether to stream the response
                  default: false
                temperature:
                  type: number
                  description: Sampling temperature
                  minimum: 0
                  maximum: 2
                  default: 0.7
                max_tokens:
                  type: integer
                  description: Maximum number of tokens to generate
                  minimum: 1
                  maximum: 4096
                  default: 1024
                top_p:
                  type: number
                  description: Nucleus sampling parameter
                  minimum: 0
                  maximum: 1
                  default: 0.95
                stop:
                  type: array
                  description: Sequences where the API will stop generating
                  items:
                    type: string
                  nullable: true
              required:
              - messages
              - model
            example:
              model: RedHatAI/DeepSeek-R1-Distill-Qwen-32B-FP8-dynamic
              messages:
              - role: system
                content: Act as a helpful assistant to the user
              - role: user
                content: Give me a travel itinerary for a 7-day trip to Japan
              stream: false
              temperature: 0.7
              max_tokens: 1024
              top_p: 0.9
              stop: null
      responses:
        '200':
          description: Successful chat completion
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                    description: Unique identifier for the completion
                  choices:
                    type: array
                    items:
                      type: object
                      properties:
                        delta:
                          type: object
                          properties:
                            content:
                              type: string
                              description: Generated text content
                        index:
                          type: integer
                          description: Index of the choice
                        finish_reason:
                          type: string
                          enum:
                          - stop
                          - length
                          - content_filter
                          description: Reason for finishing the generation
        '400':
          description: Invalid request parameters
        '401':
          description: Unauthorized - Invalid token
        '500':
          description: Internal server error
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: JWT token for authentication