LiteLLM
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
LiteLLM scores 8.1/10 (Strong) in Gateways & Routers.
Language Python License MIT Stars 52.5k★ Type service Self-host Yes Repo BerriAI/litellm Homepage https://litellm.ai
Quality
Strong 8.1
Adoption 68
Activity 89
Maturity 96
Community 75
Capability 50
Show the math
Overall 8.1/10
value = 8.1/10
score = value
Adoption 7.1/10
value = 68/100
score = 1 + 9 * value / 100
Activity 9/10
value = 89.4/100
score = 1 + 9 * value / 100
Maturity 9.6/10
value = 95.8/100
score = 1 + 9 * value / 100
Community 7.7/10
value = 74.6/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
52.5k★ GitHub stars
3.5k/90d Recent commits
14 devs/90d Recent contributors
2.9y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
- Managed option
Managed option
Available as a hosted/managed service in addition to self-hosting.
gateway proxy openai-compatible routing python