Requesty

Requesty is an LLM routing and gateway platform that exposes a single OpenAI-compatible API across 300+ models from providers like OpenAI, Anthropic, DeepSeek, and Together AI. The Requesty Router adds intelligent routing, automatic fallbacks, response caching, spend controls, and per-request cost observability on top of unified inference.

4 APIs 0 Features

AILLMRoutingGatewayObservability

APIs

Requesty Chat Completions API

OpenAI-compatible chat completions routed across 300+ models from OpenAI, Anthropic, DeepSeek, Together AI, and more, with streaming, tool use, web search, automatic fallbacks, ...

Requesty Models API

Lists the 300+ models routable through the Requesty gateway with their identifiers, provider, context length, and per-token pricing.

Requesty Usage & Analytics API

Retrieves per-key and organization-level usage statistics, request cost, and spend reporting for observability and FinOps across the gateway.

Requesty API Keys API

Programmatically create, list, inspect, and delete API keys and manage their spending limits, labels, and expiration for governing gateway access.

Collections

Requesty Router API

OPEN

Pricing Plans

Requesty Plans Pricing

3 plans

PLANS

Rate Limits

Requesty Rate Limits

5 limits

RATE LIMITS

FinOps

Requesty Finops

FINOPS

Event Specifications

Requesty Chat Completions Streaming (HTTP + SSE)

AsyncAPI 2.6 description of Requesty's **chat completion streaming** surface. Requesty does not publish a WebSocket API. The only asynchronous / event-style transport documented...

ASYNCAPI

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Requesty Router API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create a chat completion
      type: http
    http:
      method: POST
      url: https://router.requesty.ai/v1/chat/completions
      body:
        type: json
        data: "{\n  \"model\": \"openai/gpt-4o-mini\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\"\
          : \"Hello!\"\n    }\n  ],\n  \"max_tokens\": 256,\n  \"temperature\": 1,\n  \"stream\": false\n}"
    docs: Routes an OpenAI-compatible chat completion across 300+ models. Set stream=true for Server-Sent Events streaming.
- info:
    name: Embeddings
    type: folder
  items:
  - info:
      name: Create embeddings
      type: http
    http:
      method: POST
      url: https://router.requesty.ai/v1/embeddings
      body:
        type: json
        data: "{\n  \"model\": \"openai/text-embedding-3-small\",\n  \"input\": \"The quick brown fox.\"\n}"
    docs: Generates vector embeddings for the supplied input using a routed embedding model.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List models
      type: http
    http:
      method: GET
      url: https://router.requesty.ai/v1/models
    docs: Lists the 300+ models routable through Requesty with metadata and pricing.
- info:
    name: API Keys
    type: folder
  items:
  - info:
      name: List API keys
      type: http
    http:
      method: GET
      url: https://router.requesty.ai/v1/api-keys
    docs: Lists all API keys for the authenticated account.
  - info:
      name: Create an API key
      type: http
    http:
      method: POST
      url: https://router.requesty.ai/v1/api-keys
      body:
        type: json
        data: "{\n  \"name\": \"my-key\",\n  \"limit\": 100,\n  \"labels\": [\"prod\"]\n}"
    docs: Creates a new API key with optional spending limit, labels, and expiry.
  - info:
      name: Get an API key
      type: http
    http:
      method: GET
      url: https://router.requesty.ai/v1/api-keys/:key_id
    docs: Gets details for a specific API key.
  - info:
      name: Update API key spending limit
      type: http
    http:
      method: PATCH
      url: https://router.requesty.ai/v1/api-keys/:key_id/limit
      body:
        type: json
        data: "{\n  \"limit\": 250\n}"
    docs: Updates the USD spending limit for a specific API key.
  - info:
      name: Delete an API key
      type: http
    http:
      method: DELETE
      url: https://router.requesty.ai/v1/api-keys/:key_id
    docs: Deletes a specific API key.
- info:
    name: Usage
    type: folder
  items:
  - info:
      name: Get API key usage
      type: http
    http:
      method: GET
      url: https://router.requesty.ai/v1/api-keys/:key_id/usage
    docs: Retrieves usage statistics and spend for a specific API key.
  - info:
      name: Get organization usage
      type: http
    http:
      method: GET
      url: https://router.requesty.ai/v1/organization/usage
    docs: Retrieves aggregated usage statistics and spend across the organization.