openapi: 3.1.0
info:
  title: LLM Metrics API
  description: Metrics and analytics for LLM model inference
  version: '1.0.0'

servers:
  - url: 'https://http.llm.proxy.prod.s9t.link'
    description: LLM Production Server

tags:
  - name: Metrics
    description: Performance and usage metrics for LLM requests

paths:
  /get/metrics/{request_id}:
    get:
      tags:
        - Metrics
      summary: Get metrics for any LLM chat completion request
      description: Retrieve detailed metrics about token counts, processing time, and performance statistics
      operationId: getChatMetrics
      parameters:
        - name: request_id
          in: path
          required: true
          schema:
            type: string
            format: uuid
          description: The ID of the chat completion request
      responses:
        '200':
          description: Successful metrics retrieval
          content:
            application/json:
              schema:
                type: object
                required:
                  - input_tokens
                  - output_tokens
                  - time_taken
                properties:
                  input_tokens:
                    type: integer
                    description: Number of input tokens processed
                    example: 41
                  output_tokens:
                    type: integer
                    description: Number of tokens generated
                    example: 758
                  time_taken:
                    type: number
                    description: Total processing time in seconds
                    example: 1.25
                  time_after_first_token:
                    type: number
                    description: Time taken after first token generation
                    example: 1.21
        '404':
          description: Metrics not found
        '500':
          description: Internal server error

components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: JWT token for authentication

security:
  - BearerAuth: [] 