LiteLLM
Unified API to call 100+ LLM providers with OpenAI format
About
LiteLLM is an open-source AI gateway that exposes a single OpenAI-format interface for calling more than a hundred LLM providers including OpenAI, Anthropic, Gemini, Bedrock, and Azure. It works as a Python SDK for direct integration or as a proxy server that centralizes routing, load balancing, fallbacks, and spend tracking for a team. It standardizes multi-provider access behind one API. Released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- LLM Inference & Serving
- Price
- Free
- Platform
- Hybrid
- Difficulty
- Easy (2/5)
- License
- MIT
- Added
- Jan 29, 2026
Related Tools
Port of Meta's LLaMA model in C/C++ for efficient CPU inference
High-throughput LLM serving engine with PagedAttention
Minimalist ML framework in Rust by Hugging Face for fast inference.
Optimized inference library for running quantized LLMs on consumer GPUs.
Open-source ChatGPT alternative that runs 100% offline on your computer.
Fast LLM inference on consumer GPUs using neuron-aware sparse computation.
Mentioned in
From OpenAI to LiteLLM: Cutting the AI Bill with Smart Routing
A first-person take on putting LiteLLM in front of OpenAI, Anthropic, and a local Ollama instance, with...
Billy C
Self-Hosting an Open WebUI ChatGPT Clone with Model Rotation
A practical walkthrough for standing up Open WebUI on your own box, plugging Ollama in for local models, and...
Billy C
15 Open-Source AI Dev Tools You Should Know About
The best free and open-source AI tools for developers that deserve more attention.
Max P