RightNow AI Rerank API

openapi: 3.1.0
info:
  title: RunInfra Audio Rerank API
  description: OpenAI-compatible HTTP API for verified RunInfra inference deployments.
  version: '2026-04-24'
  contact:
    name: RunInfra support
    email: jaber@runinfra.ai
    url: https://runinfra.ai/contact
servers:
- url: https://api.runinfra.ai/v1
  description: Production
security:
- bearerAuth: []
tags:
- name: Rerank
paths:
  /rerank:
    post:
      operationId: createRerank
      summary: Rerank documents
      description: Text reranking for verified TEI deployments and multimodal document reranking for compatible vLLM vision rerank deployments. Flat workspace requests are replay-safe when an Idempotency-Key is provided; pipeline-scoped rerank helpers are sent once.
      tags:
      - Rerank
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RerankRequest'
      responses:
        '200':
          description: Rerank response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RerankResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '409':
          $ref: '#/components/responses/Conflict'
        '422':
          $ref: '#/components/responses/UnprocessableEntity'
        '429':
          $ref: '#/components/responses/RateLimited'
        '500':
          $ref: '#/components/responses/InternalServerError'
        '502':
          $ref: '#/components/responses/BadGateway'
        '503':
          $ref: '#/components/responses/Unavailable'
        '504':
          $ref: '#/components/responses/GatewayTimeout'
components:
  responses:
    RateLimited:
      description: Rate limit exceeded
      headers:
        Retry-After:
          schema:
            type: integer
          description: Seconds to wait before retrying
        X-RateLimit-Remaining:
          schema:
            type: integer
          description: Remaining requests in the window
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    NotFound:
      description: Model or deployment not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    GatewayTimeout:
      description: Gateway timeout
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    UnprocessableEntity:
      description: Request cannot be replayed or processed safely
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    PaymentRequired:
      description: Insufficient credits
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    InternalServerError:
      description: Unexpected gateway error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    BadGateway:
      description: Upstream serving backend transient failure
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Forbidden:
      description: Key scope mismatch or plan limit exceeded
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Missing or invalid API key
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unavailable:
      description: Endpoint stopped, provisioning, or at capacity
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Conflict:
      description: Idempotency conflict
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    BadRequest:
      description: Malformed request
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    Error:
      type: object
      properties:
        error:
          type: object
          required:
          - message
          - type
          properties:
            message:
              type: string
            type:
              type: string
            param:
              type: string
              nullable: true
            code:
              type: string
              nullable: true
    RerankResult:
      type: object
      required:
      - index
      - score
      properties:
        index:
          type: integer
        score:
          type: number
        id:
          type: string
        text:
          type: string
        content:
          type: array
          items:
            $ref: '#/components/schemas/RerankContentPart'
    RerankRequest:
      type: object
      required:
      - model
      - query
      properties:
        model:
          type: string
          example: bge-reranker-v2-m3
        query:
          type: string
          example: What is RunInfra Instant Start?
        texts:
          type: array
          items:
            type: string
          minItems: 1
          maxItems: 500
        documents:
          type: array
          items:
            $ref: '#/components/schemas/RerankDocument'
          minItems: 1
          maxItems: 500
        top_n:
          type: integer
          minimum: 1
          description: Optional number of ranked results to return.
      oneOf:
      - required:
        - texts
      - required:
        - documents
    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer
    RerankScore:
      type: object
      required:
      - index
      - score
      properties:
        index:
          type: integer
        score:
          type: number
    RerankContentPart:
      oneOf:
      - type: object
        required:
        - type
        - text
        properties:
          type:
            const: text
          text:
            type: string
      - type: object
        required:
        - type
        - image_url
        properties:
          type:
            const: image_url
          image_url:
            oneOf:
            - type: string
            - type: object
              required:
              - url
              properties:
                url:
                  type: string
      - type: object
        required:
        - type
        - video_url
        properties:
          type:
            const: video_url
          video_url:
            oneOf:
            - type: string
            - type: object
              required:
              - url
              properties:
                url:
                  type: string
    RerankResponse:
      type: object
      required:
      - object
      - model
      - scores
      - rankings
      - results
      - document_count
      properties:
        object:
          type: string
          example: runinfra.rerank
        model:
          type: string
        upstream_model:
          type: string
        scores:
          type: array
          items:
            $ref: '#/components/schemas/RerankScore'
        rankings:
          type: array
          items:
            $ref: '#/components/schemas/RerankResult'
        results:
          type: array
          items:
            $ref: '#/components/schemas/RerankResult'
        document_count:
          type: integer
        usage:
          $ref: '#/components/schemas/Usage'
    RerankDocument:
      oneOf:
      - type: string
      - type: object
        required:
        - text
        properties:
          id:
            type: string
          text:
            type: string
      - type: object
        required:
        - content
        description: Multimodal document shape for compatible vLLM vision rerank deployments. TEI rerank deployments are text-only.
        properties:
          id:
            type: string
          content:
            type: array
            minItems: 1
            items:
              $ref: '#/components/schemas/RerankContentPart'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: RunInfra API key. Generate at https://runinfra.ai/settings/api-keys