openapi: 3.1.0
info:
  title: Llama-4-Maverick-17B-fp8
  description: High-capacity LLM for complex tasks
  version: '1.0.0'

servers:
  - url: https://http.llama-4-maverick-17b-fp8-proxy.yotta-infrastructure.on-prem.clusters.s9t.link
    description: Production LLM Proxy Server

tags:
  - name: Chat Completion
    description: Large Language Model chat completion services

paths:
  /chat/completions: 
    post:
      tags:
        - Chat Completion
      summary: Create chat completion with lama-4-Maverick-17B-fp8
      description: Create a chat completion for given messages with streaming support
      operationId: createChatCompletion70B
      parameters:
        - in: header
          name: id
          schema:
            type: string
            default: "9cb8d60c-6e8a-4f92-a2ab-a42e3e6a7349"
          required: true
          description: Model UUID for the request
          example: "9cb8d60c-6e8a-4f92-a2ab-a42e3e6a7349"
      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: [llama3_1]
                  default: "llama3_1"
                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: "llama3_1"
              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: 0.90
              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

security:
  - BearerAuth: []