Requesty Models API

openapi: 3.0.1
info:
  title: Requesty Router API
  description: >-
    OpenAI-compatible LLM gateway that routes a single API across 300+ models
    from providers such as OpenAI, Anthropic, DeepSeek, and Together AI, adding
    intelligent routing, automatic fallbacks, response caching, spend controls,
    and per-request cost observability. This specification covers the documented
    inference (chat completions, embeddings, models) and management (API keys,
    usage/analytics) endpoints of the Requesty Router.
  termsOfService: https://www.requesty.ai/terms
  contact:
    name: Requesty Support
    email: support@requesty.ai
  version: '1.0'
servers:
  - url: https://router.requesty.ai/v1
    description: Global router
  - url: https://router.eu.requesty.ai/v1
    description: EU data residency router
security:
  - bearerAuth: []
tags:
  - name: Chat
    description: OpenAI-compatible chat completions routed across providers.
  - name: Embeddings
    description: Vector embedding generation.
  - name: Models
    description: Catalog of routable models.
  - name: API Keys
    description: Programmatic management of Requesty API keys.
  - name: Usage
    description: Usage statistics and spend reporting.
paths:
  /chat/completions:
    post:
      operationId: createChatCompletion
      tags:
        - Chat
      summary: Create a chat completion
      description: >-
        Creates a model response for the given chat conversation. Requesty
        routes the request to the best available provider for the requested
        model, applying fallbacks and caching. OpenAI-compatible. Set
        `stream: true` to receive the response as Server-Sent Events.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateChatCompletionRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateChatCompletionResponse'
            text/event-stream:
              schema:
                type: string
                description: Server-Sent Events stream of chat completion chunks when stream=true.
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '429':
          description: Too many requests
  /embeddings:
    post:
      operationId: createEmbedding
      tags:
        - Embeddings
      summary: Create embeddings
      description: Generates vector embeddings for the supplied input text using a routed embedding model.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateEmbeddingRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateEmbeddingResponse'
  /models:
    get:
      operationId: listModels
      tags:
        - Models
      summary: List models
      description: Lists the models available through the Requesty Router with metadata and pricing.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListModelsResponse'
  /api-keys:
    get:
      operationId: listApiKeys
      tags:
        - API Keys
      summary: List API keys
      description: Lists all API keys for the authenticated account.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListApiKeysResponse'
    post:
      operationId: createApiKey
      tags:
        - API Keys
      summary: Create an API key
      description: Creates a new API key with optional spending limit, labels, and expiry.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateApiKeyRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiKey'
  /api-keys/{key_id}:
    get:
      operationId: getApiKey
      tags:
        - API Keys
      summary: Get an API key
      parameters:
        - $ref: '#/components/parameters/KeyId'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiKey'
    delete:
      operationId: deleteApiKey
      tags:
        - API Keys
      summary: Delete an API key
      parameters:
        - $ref: '#/components/parameters/KeyId'
      responses:
        '200':
          description: OK
  /api-keys/{key_id}/usage:
    get:
      operationId: getApiKeyUsage
      tags:
        - Usage
      summary: Get API key usage
      description: Retrieves usage statistics and spend for a specific API key.
      parameters:
        - $ref: '#/components/parameters/KeyId'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UsageReport'
  /api-keys/{key_id}/limit:
    patch:
      operationId: updateApiKeyLimit
      tags:
        - API Keys
      summary: Update API key spending limit
      parameters:
        - $ref: '#/components/parameters/KeyId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                limit:
                  type: number
                  description: Spending limit in USD.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiKey'
  /organization/usage:
    get:
      operationId: getOrganizationUsage
      tags:
        - Usage
      summary: Get organization usage
      description: Retrieves aggregated usage statistics and spend across the organization.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UsageReport'
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: Requesty API key passed as a Bearer token in the Authorization header.
  parameters:
    KeyId:
      name: key_id
      in: path
      required: true
      description: Identifier of the API key.
      schema:
        type: string
  schemas:
    CreateChatCompletionRequest:
      type: object
      required:
        - messages
      properties:
        model:
          type: string
          description: Routed model identifier, e.g. `openai/gpt-4o-mini` or `anthropic/claude-sonnet-4-20250514`. Defaults to `openai/gpt-4o-mini`.
          default: openai/gpt-4o-mini
        messages:
          type: array
          description: A list of messages comprising the conversation so far.
          items:
            $ref: '#/components/schemas/ChatMessage'
        max_tokens:
          type: integer
          description: Maximum number of tokens to generate.
        temperature:
          type: number
          description: Sampling temperature between 0 and 2.
          default: 1
        top_p:
          type: number
          description: Nucleus sampling probability mass.
        stream:
          type: boolean
          description: If true, partial deltas are streamed as Server-Sent Events.
          default: false
        tools:
          type: array
          description: A list of tools the model may call, such as custom functions or built-in web_search.
          items:
            type: object
        tool_choice:
          description: Controls which (if any) tool is called by the model.
          oneOf:
            - type: string
            - type: object
        response_format:
          type: object
          description: An object specifying the format the model must output (e.g. JSON / structured outputs), where supported by the routed model.
    ChatMessage:
      type: object
      required:
        - role
        - content
      properties:
        role:
          type: string
          enum:
            - system
            - user
            - assistant
            - tool
        content:
          description: The contents of the message; string or array of content parts.
          oneOf:
            - type: string
            - type: array
              items:
                type: object
    CreateChatCompletionResponse:
      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:
          $ref: '#/components/schemas/Usage'
    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer
        cost:
          type: number
          description: Requesty USD cost for the request.
    CreateEmbeddingRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
        input:
          description: Input text or array of text to embed.
          oneOf:
            - type: string
            - type: array
              items:
                type: string
    CreateEmbeddingResponse:
      type: object
      properties:
        object:
          type: string
          example: list
        data:
          type: array
          items:
            type: object
            properties:
              object:
                type: string
                example: embedding
              index:
                type: integer
              embedding:
                type: array
                items:
                  type: number
        model:
          type: string
        usage:
          $ref: '#/components/schemas/Usage'
    ListModelsResponse:
      type: object
      properties:
        object:
          type: string
          example: list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
    Model:
      type: object
      properties:
        id:
          type: string
          description: Routed model identifier, e.g. `openai/gpt-4o`.
        object:
          type: string
          example: model
        owned_by:
          type: string
          description: Upstream provider.
        context_window:
          type: integer
          description: Maximum context length supported.
        input_price:
          type: number
          description: Input price per million tokens in USD.
        output_price:
          type: number
          description: Output price per million tokens in USD.
    ListApiKeysResponse:
      type: object
      properties:
        data:
          type: array
          items:
            $ref: '#/components/schemas/ApiKey'
    CreateApiKeyRequest:
      type: object
      properties:
        name:
          type: string
        limit:
          type: number
          description: Optional spending limit in USD.
        labels:
          type: array
          items:
            type: string
        expiry:
          type: string
          format: date-time
    ApiKey:
      type: object
      properties:
        id:
          type: string
        name:
          type: string
        key:
          type: string
          description: The API key value, returned only on creation.
        limit:
          type: number
        labels:
          type: array
          items:
            type: string
        expiry:
          type: string
          format: date-time
        created_at:
          type: string
          format: date-time
    UsageReport:
      type: object
      properties:
        total_cost:
          type: number
          description: Total spend in USD over the reporting window.
        total_requests:
          type: integer
        total_tokens:
          type: integer
        breakdown:
          type: array
          description: Per-model or per-key usage breakdown.
          items:
            type: object
            properties:
              model:
                type: string
              requests:
                type: integer
              tokens:
                type: integer
              cost:
                type: number