The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Python ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai
# OpenAI
OPENAI_API_KEY = ""
OPENAI_BASE_URL = ""
# Cohere
COHERE_API_KEY = ""
# OpenRouter
OR_SITE_URL = ""
OR_APP_NAME = "LiteLLM Example app"
OR_API_KEY = ""
# Azure API base URL
AZURE_API_BASE = ""
# Azure API version
AZURE_API_VERSION = ""
# Azure API key
AZURE_API_KEY = ""
# Replicate
REPLICATE_API_KEY = ""
REPLICATE_API_TOKEN = ""
# Anthropic
ANTHROPIC_API_KEY = ""
# Infisical
INFISICAL_TOKEN = ""
# Novita AI
NOVITA_API_KEY = ""
# INFINITY
INFINITY_API_KEY = ""
# Development Configs
# Generate one with: echo "LITELLM_MASTER_KEY=sk-$(openssl rand -hex 32)"
LITELLM_MASTER_KEY = ""
DATABASE_URL = "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
STORE_MODEL_IN_DB = "True"