LiteLLM
Open-source gateway that calls 100+ LLMs with one OpenAI-style API.
Overview
LiteLLM is a Python SDK and proxy server that normalizes requests to more than 100 providers behind an OpenAI-compatible interface. Teams use it to manage keys, budgets, rate limits and fallbacks for BYOK apps.
- Unified OpenAI-style API
- Virtual keys and budgets
- Fallbacks and load balancing
- Logging integrations
Our verdict
What we like
- Makes any app multi-provider
- Team cost control
Watch out for
- Another service to operate
Works with these providers
Keys from these providers work in this app. Usage is billed by the provider at its list price.
BYOK Key Safety Score
Key handling in LiteLLM
Grade B
Your key is stored by the service (usually encrypted) and requests may route through its servers.
- Key storage18/40
Key is held by the vendor, so you rely on their security.
- Auditable code25/25
Open source: anyone can verify how keys are handled.
- Self-hosting15/15
Can run entirely on your own infrastructure.
- Offline option10/10
Supports local models, so no key is needed at all for private work.
- Provider choice10/10
15 provider options, which lets you pick the provider whose data terms you trust.
Whatever the score, give each app its own key, set a monthly spend limit with your provider, and revoke keys you no longer use. Read the key-safety checklist.
LiteLLM FAQ
- Does LiteLLM support bring your own key?
- Yes. LiteLLM accepts your own API key from OpenAI, Anthropic, Google Gemini, OpenRouter, Mistral, Groq, DeepSeek, xAI, Ollama, Azure OpenAI, AWS Bedrock, Perplexity, Together AI, Cohere and OpenAI-compatible. Usage is billed by the provider at its API rates.
- Where does LiteLLM store my API key?
- On the vendor's servers, and requests may be routed through them. Its BYOK Tools Key Safety Score is 78/100.
- Is LiteLLM free?
- Open source: Free & open source; enterprise tier. API usage is billed separately by your model provider.
- Is LiteLLM open source?
- Yes. The source code is at https://github.com/BerriAI/litellm. It can also be self-hosted.
- Can LiteLLM run local models?
- Yes. It can connect to local runtimes such as Ollama or LM Studio, so no API key is needed for private or offline use.
- Which platforms does LiteLLM support?
- Self-hosted, CLI.
Community reviews
No reviews yet.
Alternatives to LiteLLM
All automation & agents →n8n
Automation & Agents
Fair-code workflow automation with AI agent nodes and your own keys.
Dify
Automation & Agents
Open-source platform for building LLM apps, agents and RAG pipelines.
Flowise
Automation & Agents
Drag-and-drop builder for LLM agents and chatflows.
Langflow
Automation & Agents
Visual framework for building multi-agent and RAG applications.
CrewAI
Automation & Agents
Framework for orchestrating role-playing multi-agent teams.
Browser Use
Automation & Agents
Open-source library and CLI that lets LLM agents control a real browser.