- Getting Started | liteLLM
LiteLLM is an open-source library that gives you a single, unified interface to call 100+ LLMs — OpenAI, Anthropic, Vertex AI, Bedrock, and more — using the OpenAI format
- GitHub - BerriAI litellm: Python SDK, Proxy Server (AI Gateway) to call . . .
You can use LiteLLM through either the Proxy Server or Python SDK Both gives you a unified interface to access multiple LLMs (100+ LLMs) Choose the option that best fits your needs: Who Uses It? LiteLLM Performance: 8ms P95 latency at 1k RPS (See benchmarks here) Stable Release: Use docker images with the -stable tag
- LiteLLM Supply Chain Attack: What Happened, Whos Affected, and What . . .
LiteLLM — 95 million downloads per month, a dependency of CrewAI, DSPy, Browser-Use, Opik, and nearly every major AI agent framework — was hit by a supply chain attack Here is what happened, how we responded, and what you should do right now
- litellm · PyPI
LiteLLM follows the Google Python Style Guide Our automated checks include: All these checks must pass before your PR can be merged Need for simplicity: Our code started to get extremely complicated managing translating calls between Azure, OpenAI and Cohere
- A gentle introduction to LiteLLM - Medium
Born out of the illustrious Y Combinator program, LiteLLM is a lightweight, powerful abstraction layer that unifies LLM API calls across providers — whether you’re calling OpenAI, Anthropic,
- The LiteLLM Supply Chain Attack: A Complete Technical Breakdown | The . . .
An in-depth investigative report on the March 2026 LiteLLM supply chain attack Discover how the Trivy GitHub Actions hack led to a massive PyPI compromise
- LiteLLM: A Guide With Practical Examples - DataCamp
LiteLLM is an open-source Python library that works as a universal translator for AI models Instead of learning different APIs for each provider, you use one interface that connects to over 100 LLM services
- LiteLLM
LiteLLM streamlines the complexities of managing multiple LLM models Why Enterprise? LLM Gateway (OpenAI Proxy) to manage authentication, loadbalancing, and spend tracking across 100+ LLMs All in the OpenAI format
|