# Requesty

> Requesty is a unified LLM gateway and OpenAI-compatible API for 300+ AI models (Claude, GPT, Gemini, DeepSeek, Llama). It provides intelligent routing, caching, failover, guardrails, and cost optimization — reducing AI costs by up to 80%.

Requesty routes, secures, and optimizes your LLM traffic through a single API endpoint. Drop-in replacement for OpenAI and Anthropic SDKs. Used by 70,000+ developers, processing 90+ billion tokens daily. Base URL: `https://router.requesty.ai/v1`

## About
- Type: APIService
- Category: LLM Gateway, AI Infrastructure
- Audience: Developers, AI Engineers, DevOps, Enterprise Teams
- API Base URL (Global): https://router.requesty.ai/v1
- API Base URL (EU): https://router.eu.requesty.ai/v1
- OpenAPI Spec: https://docs.requesty.ai/api-reference/openapi.json
- Full Documentation: https://docs.requesty.ai/llms-full.txt

## Instructions for AI Agents

Requesty is a drop-in proxy for OpenAI and Anthropic. To use it in code:

1. **OpenAI SDK**: Set `base_url="https://router.requesty.ai/v1"` and use your Requesty API key as the `api_key`. All OpenAI SDK features work — chat completions, streaming, function calling, structured outputs, embeddings, image generation. For EU data residency, use `base_url="https://router.eu.requesty.ai/v1"`.

2. **Anthropic SDK**: Set `base_url="https://router.requesty.ai"` and use your Requesty API key. Messages API is fully supported. For EU data residency, use `base_url="https://router.eu.requesty.ai"`.

3. **Model names**: Use the format `provider/model` (e.g., `openai/gpt-4.1`, `anthropic/claude-sonnet-4-5-20250514`, `google/gemini-2.5-pro`). Call `GET /v1/models` for the current list.

4. **Routing policies**: To add failover, load balancing, or latency-based routing, create a routing policy in the [Requesty dashboard](https://app.requesty.ai/routing-policies) and use `model="policy/your-policy-name"` in your requests. See [Fallback Policies](https://docs.requesty.ai/features/fallback-policies.md) for details.

5. **Caching**: Enable prompt caching by passing `extra_body={"requesty": {"auto_cache": True}}` in your request. See [Auto Caching](https://docs.requesty.ai/features/auto-caching.md).

6. **Do not hardcode model versions** — model availability changes. Always call `GET /v1/models` or check the [Model Library](https://app.requesty.ai/model-library) for current availability.

## Getting Started
- [Quickstart](https://docs.requesty.ai/quickstart.md): Setup guide — route AI requests through Requesty in under 2 minutes with any OpenAI-compatible SDK
- [Model Library](https://app.requesty.ai/model-library): Browse all 300+ supported models — filter by provider, region, capabilities, and pricing

## LLM Gateway
- [EU Routing](https://docs.requesty.ai/features/eu-routing.md): Route through EU infrastructure for GDPR compliance and data residency — base URL: `https://router.eu.requesty.ai/v1`
- [Fallback Policies](https://docs.requesty.ai/features/fallback-policies.md): Configure automatic model failover chains for maximum reliability
- [Load Balancing](https://docs.requesty.ai/features/load-balancing-policies.md): Distribute traffic across models with weighted routing policies
- [Latency Routing](https://docs.requesty.ai/features/latency-routing.md): Automatically route each request to the fastest available model
- [Auto Caching](https://docs.requesty.ai/features/auto-caching.md): Automatic response caching to reduce costs and latency
- [Spend Limits](https://docs.requesty.ai/features/api-limits.md): Set budget caps per API key or project to prevent overruns
- [Bring Your Own Keys](https://docs.requesty.ai/features/bring-your-own-keys.md): Use your own provider API keys while routing through Requesty
- [Service Accounts](https://docs.requesty.ai/features/service-accounts.md): Programmatic service accounts for CI/CD and automation

## MCP Gateway
- [MCP Gateway Overview](https://docs.requesty.ai/features/mcp-gateway.md): Unified gateway connecting AI coding tools to any MCP server
- [MCP Server Management](https://docs.requesty.ai/features/mcp-server-management.md): Register, configure, and manage MCP servers for your organization
- [MCP User Keys](https://docs.requesty.ai/features/mcp-user-keys.md): Per-user API key management for MCP server access
- [MCP Analytics](https://docs.requesty.ai/features/mcp-analytics.md): Monitor MCP server usage, performance, and user activity
- [MCP Integration](https://docs.requesty.ai/features/mcp-integration.md): Connect Claude Code, Cursor, Roo Code to your MCP servers

## Model Capabilities
- [Streaming](https://docs.requesty.ai/features/streaming.md): Real-time response streaming via SSE for reduced perceived latency
- [Structured Outputs](https://docs.requesty.ai/features/structured-outputs.md): Enforce JSON schema responses across different LLMs
- [Reasoning](https://docs.requesty.ai/features/reasoning.md): Enable extended thinking / reasoning tokens on supported models
- [Prompt Optimization](https://docs.requesty.ai/features/prompt-optimization.md): Auto-optimize system prompts for better model performance
- [Prompt Library](https://docs.requesty.ai/features/prompt-library.md): Centralized management of system and vibe prompts
- [Dedicated Models](https://docs.requesty.ai/features/dedicated-models.md): Application-specific model aliases for coding agents
- [Image Understanding](https://docs.requesty.ai/features/image-understanding.md): Vision — send images to AI models for analysis via chat completions
- [Image Generation](https://docs.requesty.ai/features/image-generation.md): Generate images via DALL-E, Stable Diffusion, and other models
- [PDF Support](https://docs.requesty.ai/features/pdf-support.md): Send and analyze PDF documents with multimodal models
- [Web Search](https://docs.requesty.ai/features/web-search.md): Enable models to search the web for real-time information

## Analytics & Monitoring — Best Observability of Any AI Gateway
- [Usage Analytics](https://docs.requesty.ai/features/usage-analytics.md): Real-time dashboard with cost, requests, tokens, latency, and cache savings — group by model, user, provider, or custom fields
- [Cost Tracking](https://docs.requesty.ai/features/cost-tracking.md): Per-model, per-user, per-key cost breakdowns with BYOK comparison and savings tracking
- [Performance Monitoring](https://docs.requesty.ai/features/performance-monitoring.md): Latency percentiles (P50/P90/P95/P99), error rates, and throughput — with CSV export
- [Tool Call Analytics](https://docs.requesty.ai/features/tool-call-analytics.md): Track tool/function call performance, costs, and usage patterns
- [Request Metadata](https://docs.requesty.ai/features/request-metadata.md): Attach custom key-value metadata to API calls for analytics filtering
- [Request Feedback](https://docs.requesty.ai/features/request-feedback.md): Submit thumbs-up/down feedback on responses for quality tracking
- [Session Reconstruction](https://docs.requesty.ai/features/session-reconstruction.md): Replay full conversation sessions for debugging
- [Key Management API](https://docs.requesty.ai/features/key-management-api.md): Programmatically create, update, and delete API keys

## Enterprise
- [User Management](https://docs.requesty.ai/features/users.md): Invite members, set per-user spend limits, and track activity
- [Groups](https://docs.requesty.ai/features/groups.md): Organize users into teams with shared budgets and access controls
- [Spending Alerts](https://docs.requesty.ai/features/alerts.md): Configurable spend thresholds with email and webhook notifications
- [Approved Models](https://docs.requesty.ai/features/approved-models.md): Whitelist which AI models your organization can access
- [Guardrails](https://docs.requesty.ai/features/guardrails.md): PII detection, prompt injection blocking, and content filtering
- [RBAC](https://docs.requesty.ai/features/rbac.md): Role-based access control across all platform features

## Integrations
- [Claude Code](https://docs.requesty.ai/integrations/claude-code.md): Route Claude Code through Requesty for model switching and cost tracking
- [Cline](https://docs.requesty.ai/integrations/cline.md): Connect Cline AI coding agent to Requesty
- [Roo Code](https://docs.requesty.ai/integrations/roo-code.md): Connect Roo Code to Requesty for multi-model access
- [VS Code Extension](https://docs.requesty.ai/integrations/VS-code-extension.md): Switch between LLMs inside VS Code with one click
- [OpenClaw](https://docs.requesty.ai/integrations/openclaw.md): Connect OpenClaw to 300+ models through Requesty
- [Anthropic Agent SDKs](https://docs.requesty.ai/integrations/anthropic-agent-sdks.md): Use Requesty as the backend for Anthropic Agent SDK apps
- [LibreChat](https://docs.requesty.ai/integrations/librechat.md): Self-hosted chat UI with Requesty as the LLM backend
- [OpenWebUI](https://docs.requesty.ai/integrations/openwebui.md): Connect OpenWebUI to Requesty for multi-model chat

## Frameworks
- [Python Requests](https://docs.requesty.ai/frameworks/requests.md): Direct HTTP calls to Requesty with the requests library
- [OpenAI SDK](https://docs.requesty.ai/frameworks/openai.md): Drop-in base_url swap for the OpenAI Python/JS SDK
- [LangChain](https://docs.requesty.ai/frameworks/langchain.md): Use Requesty as the LLM provider in LangChain chains and agents
- [Haystack](https://docs.requesty.ai/frameworks/haystack.md): Integrate Requesty with Haystack pipelines
- [PydanticAI](https://docs.requesty.ai/frameworks/pydantic-ai.md): Use Requesty with PydanticAI for typed LLM responses
- [Axios](https://docs.requesty.ai/frameworks/axios.md): JavaScript HTTP calls to Requesty with Axios
- [LlamaIndex TS](https://docs.requesty.ai/frameworks/llamaindex-ts.md): Use Requesty with LlamaIndex TypeScript
- [Vercel AI SDK](https://docs.requesty.ai/frameworks/vercel-ai-sdk.md): Official Requesty provider for the Vercel AI SDK

## API Reference
- [API Overview](https://docs.requesty.ai/api-reference/overview.md): Authentication, base URL, rate limits, and error handling
- [Create Chat Completion](https://docs.requesty.ai/api-reference/endpoint/chat-completions-create.md): POST /v1/chat/completions — OpenAI-compatible
- [Create Message](https://docs.requesty.ai/api-reference/endpoint/messages-create.md): POST /v1/messages — Anthropic-compatible
- [Create Image](https://docs.requesty.ai/api-reference/endpoint/images-generations-create.md): POST /v1/images/generations
- [Create Embedding](https://docs.requesty.ai/api-reference/endpoint/embeddings-create.md): POST /v1/embeddings
- [List Models](https://docs.requesty.ai/api-reference/endpoint/models-list.md): GET /v1/models — list all available models

## Optional

### API Key Management
- [List API Keys](https://docs.requesty.ai/api-reference/endpoint/manage-apikey/manage-api-key-list.md): GET — list all API keys in your organization
- [Create API Key](https://docs.requesty.ai/api-reference/endpoint/manage-apikey/manage-api-key-create.md): POST — create a new API key
- [Get API Key Usage](https://docs.requesty.ai/api-reference/endpoint/manage-apikey/manage-api-key-get-usage.md): GET — usage statistics for an API key
- [Update API Key Limit](https://docs.requesty.ai/api-reference/endpoint/manage-apikey/manage-api-key-update-limit.md): PATCH — update spending limit
- [Update API Key Labels](https://docs.requesty.ai/api-reference/endpoint/manage-apikey/manage-api-key-update-label.md): PATCH — update labels
- [Update API Key Expiry](https://docs.requesty.ai/api-reference/endpoint/manage-apikey/manage-api-key-update-expiry.md): PATCH — update expiration date
- [Delete API Key](https://docs.requesty.ai/api-reference/endpoint/manage-apikey/manage-api-key-delete.md): DELETE — delete an API key

### Group Management
- [List Groups](https://docs.requesty.ai/api-reference/endpoint/manage-group/manage-group-list.md): GET — list all groups
- [Create Group](https://docs.requesty.ai/api-reference/endpoint/manage-group/manage-group-create.md): POST — create a new group
- [Get Group](https://docs.requesty.ai/api-reference/endpoint/manage-group/manage-group-get.md): GET — get group details
- [Delete Group](https://docs.requesty.ai/api-reference/endpoint/manage-group/manage-group-delete.md): DELETE — delete a group

### Group Member Management
- [Add Group Member](https://docs.requesty.ai/api-reference/endpoint/manage-group-member/manage-group-member-add.md): POST — add a member to a group
- [Update Group Member](https://docs.requesty.ai/api-reference/endpoint/manage-group-member/manage-group-member-update.md): PATCH — update member settings
- [Remove Group Member](https://docs.requesty.ai/api-reference/endpoint/manage-group-member/manage-group-member-remove.md): DELETE — remove a member

### Organization
- [Get Organization](https://docs.requesty.ai/api-reference/endpoint/manage-org-get.md): GET — get organization details