# LiteLLM

## Docs

- [Agent-to-Agent Protocol (A2A)](https://mintlify.wiki/BerriAI/litellm/advanced/agents-a2a.md): Connect and communicate with A2A agents using LiteLLM's unified interface
- [Adding Custom Providers](https://mintlify.wiki/BerriAI/litellm/advanced/custom-providers.md): Extend LiteLLM with custom LLM providers and integrations
- [Model Context Protocol (MCP)](https://mintlify.wiki/BerriAI/litellm/advanced/mcp-tools.md): Integrate MCP servers and tools into your LiteLLM workflows
- [Prompt Management](https://mintlify.wiki/BerriAI/litellm/advanced/prompt-management.md): Centralize and version control your prompts with LiteLLM's prompt management system
- [Secret Management](https://mintlify.wiki/BerriAI/litellm/advanced/secret-management.md): Securely manage API keys and secrets with LiteLLM's secret management integrations
- [Audio APIs](https://mintlify.wiki/BerriAI/litellm/api/audio.md): Complete API reference for audio transcription and text-to-speech
- [completion()](https://mintlify.wiki/BerriAI/litellm/api/completion.md): Complete API reference for the completion() function
- [Configuration Schema](https://mintlify.wiki/BerriAI/litellm/api/config-schema.md): Complete configuration schema for LiteLLM proxy config.yaml
- [embedding()](https://mintlify.wiki/BerriAI/litellm/api/embedding.md): Complete API reference for the embedding() function
- [Environment Variables](https://mintlify.wiki/BerriAI/litellm/api/environment-variables.md): Complete reference for LiteLLM environment variables
- [Exception Types](https://mintlify.wiki/BerriAI/litellm/api/exceptions.md): Complete reference for LiteLLM exception types and error handling
- [image_generation()](https://mintlify.wiki/BerriAI/litellm/api/image-generation.md): Complete API reference for the image_generation() function
- [POST /v1/chat/completions](https://mintlify.wiki/BerriAI/litellm/api/proxy/chat-completions.md): Proxy endpoint for chat completions with authentication and logging
- [POST /v1/embeddings](https://mintlify.wiki/BerriAI/litellm/api/proxy/embeddings.md): Proxy endpoint for embeddings with authentication and tracking
- [Health Endpoints](https://mintlify.wiki/BerriAI/litellm/api/proxy/health.md): Health check and monitoring endpoints for the LiteLLM proxy
- [Key Management](https://mintlify.wiki/BerriAI/litellm/api/proxy/keys.md): API endpoints for managing API keys in the LiteLLM proxy
- [Team Management](https://mintlify.wiki/BerriAI/litellm/api/proxy/teams.md): API endpoints for managing teams in the LiteLLM proxy
- [User Management](https://mintlify.wiki/BerriAI/litellm/api/proxy/users.md): API endpoints for managing users in the LiteLLM proxy
- [Router Class](https://mintlify.wiki/BerriAI/litellm/api/router.md): Complete API reference for the Router class - load balancing and fallbacks
- [Router Configuration](https://mintlify.wiki/BerriAI/litellm/api/router-config.md): Complete guide to configuring the LiteLLM Router for load balancing
- [Docker Deployment](https://mintlify.wiki/BerriAI/litellm/deployment/docker.md): Deploy LiteLLM using Docker and Docker Compose with PostgreSQL and monitoring
- [Deploy to Fly.io](https://mintlify.wiki/BerriAI/litellm/deployment/fly-io.md): Deploy LiteLLM globally with Fly.io's edge compute platform for low-latency worldwide access
- [High Availability Deployment](https://mintlify.wiki/BerriAI/litellm/deployment/high-availability.md): Deploy LiteLLM for production with multi-region redundancy, failover, and disaster recovery
- [Kubernetes Deployment](https://mintlify.wiki/BerriAI/litellm/deployment/kubernetes.md): Deploy LiteLLM on Kubernetes using Helm charts with autoscaling and high availability
- [Monitoring and Observability](https://mintlify.wiki/BerriAI/litellm/deployment/monitoring.md): Set up comprehensive monitoring, metrics, and logging for LiteLLM with Prometheus, Grafana, and logging integrations
- [Performance Optimization](https://mintlify.wiki/BerriAI/litellm/deployment/performance.md): Optimize LiteLLM for high throughput, low latency, and efficient resource utilization
- [Deploy to Railway](https://mintlify.wiki/BerriAI/litellm/deployment/railway.md): Deploy LiteLLM to Railway with automatic provisioning and GitHub integration
- [Deploy to Render](https://mintlify.wiki/BerriAI/litellm/deployment/render.md): One-click deployment of LiteLLM to Render with automatic SSL and managed database
- [Security Best Practices](https://mintlify.wiki/BerriAI/litellm/deployment/security.md): Secure your LiteLLM deployment with authentication, network policies, secrets management, and compliance
- [Troubleshooting Guide](https://mintlify.wiki/BerriAI/litellm/deployment/troubleshooting.md): Debug common deployment issues, errors, and performance problems in LiteLLM
- [Caching Support](https://mintlify.wiki/BerriAI/litellm/features/caching.md): Reduce costs and latency with intelligent response caching
- [Cost Tracking](https://mintlify.wiki/BerriAI/litellm/features/cost-tracking.md): Monitor and control LLM API costs across providers
- [Fallback Logic](https://mintlify.wiki/BerriAI/litellm/features/fallbacks.md): Automatic failover to backup models and deployments
- [Guardrails and Safety](https://mintlify.wiki/BerriAI/litellm/features/guardrails.md): Content moderation, policy enforcement, and safety controls
- [Load Balancing](https://mintlify.wiki/BerriAI/litellm/features/loadbalancing.md): Distribute requests across multiple deployments with intelligent routing
- [Logging and Observability](https://mintlify.wiki/BerriAI/litellm/features/logging.md): Comprehensive logging, monitoring, and debugging capabilities
- [Retry Mechanisms](https://mintlify.wiki/BerriAI/litellm/features/retries.md): Automatic retry logic for failed requests with exponential backoff
- [Introduction to LiteLLM](https://mintlify.wiki/BerriAI/litellm/introduction.md): Call 100+ LLMs using the OpenAI format - Bedrock, Azure, OpenAI, VertexAI, Anthropic, Groq, and more
- [Anthropic Claude](https://mintlify.wiki/BerriAI/litellm/providers/anthropic.md): Use Claude 4.6, 3.7 Sonnet, and other Anthropic models through LiteLLM
- [Azure OpenAI](https://mintlify.wiki/BerriAI/litellm/providers/azure.md): Use OpenAI models deployed on Azure through LiteLLM
- [Batch Processing](https://mintlify.wiki/BerriAI/litellm/providers/batching.md): Process requests asynchronously at 50% lower cost with batch APIs
- [AWS Bedrock](https://mintlify.wiki/BerriAI/litellm/providers/bedrock.md): Use Claude, Llama, Mistral, and more models through AWS Bedrock
- [Cohere](https://mintlify.wiki/BerriAI/litellm/providers/cohere.md): Use Cohere's Command models for chat, embeddings, and reranking through LiteLLM
- [Embeddings](https://mintlify.wiki/BerriAI/litellm/providers/embeddings.md): Generate vector embeddings across providers for search and RAG applications
- [Function Calling](https://mintlify.wiki/BerriAI/litellm/providers/function-calling.md): Use function calling across providers with automatic format translation
- [Groq](https://mintlify.wiki/BerriAI/litellm/providers/groq.md): Use Groq's ultra-fast LLM inference with LiteLLM
- [HuggingFace](https://mintlify.wiki/BerriAI/litellm/providers/huggingface.md): Use HuggingFace models through LiteLLM's unified interface
- [Ollama](https://mintlify.wiki/BerriAI/litellm/providers/ollama.md): Run local LLMs with Ollama through LiteLLM
- [OpenAI](https://mintlify.wiki/BerriAI/litellm/providers/openai.md): Use OpenAI's GPT models through LiteLLM
- [OpenRouter](https://mintlify.wiki/BerriAI/litellm/providers/openrouter.md): Access 100+ LLMs through OpenRouter's unified API with LiteLLM
- [Provider Overview](https://mintlify.wiki/BerriAI/litellm/providers/overview.md): Call 100+ LLMs using the OpenAI format with LiteLLM
- [Streaming](https://mintlify.wiki/BerriAI/litellm/providers/streaming.md): Stream LLM responses in real-time across all providers
- [Google Vertex AI](https://mintlify.wiki/BerriAI/litellm/providers/vertex-ai.md): Use Gemini and other Google models through Vertex AI
- [Vision (Multimodal)](https://mintlify.wiki/BerriAI/litellm/providers/vision.md): Process images and vision inputs across providers
- [Budget Alerts & Monitoring](https://mintlify.wiki/BerriAI/litellm/proxy/budget-alerts.md): Configure budget tracking, alerts, and spending notifications
- [Configuration Options](https://mintlify.wiki/BerriAI/litellm/proxy/configs.md): Complete reference for LiteLLM Proxy configuration
- [Docker Deployment](https://mintlify.wiki/BerriAI/litellm/proxy/docker-deployment.md): Deploy LiteLLM Proxy using Docker and Docker Compose
- [AI Gateway Overview](https://mintlify.wiki/BerriAI/litellm/proxy/overview.md): Understanding LiteLLM's AI Gateway (Proxy) for unified LLM access
- [Quick Start Guide](https://mintlify.wiki/BerriAI/litellm/proxy/quick-start.md): Get started with LiteLLM Proxy in 5 minutes
- [Virtual Keys (API Key Management)](https://mintlify.wiki/BerriAI/litellm/proxy/virtual-keys.md): Generate and manage virtual API keys with budgets and permissions
- [Quick Start - AI Gateway (Proxy)](https://mintlify.wiki/BerriAI/litellm/quickstart-proxy.md): Deploy your LiteLLM AI Gateway in 5 minutes with authentication, cost tracking, and monitoring
- [Quick Start - Python SDK](https://mintlify.wiki/BerriAI/litellm/quickstart-sdk.md): Get started with the LiteLLM Python SDK in 2 minutes
- [Async Operations](https://mintlify.wiki/BerriAI/litellm/sdk/async.md): Use async/await for concurrent LLM calls and improved performance
- [Audio Transcription and TTS](https://mintlify.wiki/BerriAI/litellm/sdk/audio.md): Transcribe audio to text and generate speech from text
- [Chat Completion API](https://mintlify.wiki/BerriAI/litellm/sdk/completion.md): Generate chat completions using any LLM provider through a unified API
- [Embedding Generation](https://mintlify.wiki/BerriAI/litellm/sdk/embeddings.md): Generate text embeddings for semantic search, clustering, and ML tasks
- [Function/Tool Calling](https://mintlify.wiki/BerriAI/litellm/sdk/function-calling.md): Enable LLMs to call functions and use external tools
- [Image Generation](https://mintlify.wiki/BerriAI/litellm/sdk/image-generation.md): Generate images from text prompts using DALL-E, Stable Diffusion, and other providers
- [Router for Load Balancing](https://mintlify.wiki/BerriAI/litellm/sdk/router.md): Load balance across multiple LLM deployments with fallbacks, retries, and intelligent routing
- [Streaming Responses](https://mintlify.wiki/BerriAI/litellm/sdk/streaming.md): Stream chat completions token-by-token for real-time applications