LiteLLM simplifies model access, spend tracking, and fallbacks across 100+ large language models (LLMs). It provides an AI Gateway offering model access, fallbacks, and spend tracking across 100+ LLMs in the OpenAI format. Features include spend tracking, budgets & rate limits, OpenAI compatibility, LLM fallbacks, cost attribution to key/user/team/org, automatic spend tracking across multiple providers (OpenAI/Azure/Bedrock/GCP/etc.), tag-based spend tracking, logging spend to s3/gcs/etc., and prompt formatting support for Hugging Face models. Designed for platform teams to give developers LLM access easily.