Berri’s LiteLLM is an open‑source AI gateway that gives platform teams a single OpenAI‑compatible API to access over 100 LLM providers. It includes built‑in spend tracking, budgeting, rate‑limiting, automatic model fallbacks, and observability, while supporting on‑premise deployment or managed cloud service with enterprise security features such as JWT auth, SSO, and audit logs.
Funding
$1.6M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Organizations using large language models often need to integrate dozens of providers, manage API keys, enforce usage limits, and track spending, which requires custom engineering and creates operational overhead. Without a unified interface, developers may encounter inconsistent APIs, lack fallback options, and incur uncontrolled costs.
Solution
LiteLLM is an open-source AI gateway that standardizes access to over 100 LLM providers using the OpenAI API format. It offers built-in spend tracking, budgeting, and rate limiting to help platform teams monitor and control usage across multiple projects. The platform supports automatic model fallbacks, load balancing, and guardrails, ensuring reliability and compliance. LiteLLM can be deployed on-premises or used as a managed cloud service, with enterprise extensions such as JWT authentication, SSO, and audit logging. By providing a single, observable endpoint, LiteLLM reduces integration effort and enables developers to focus on building applications rather than managing LLM infrastructure.
Target Audience
Primary customers are platform engineering teams and enterprises that need to provide scalable, cost‑controlled LLM access to multiple developers and applications.
Features
- OpenAI‑compatible API layer for 100+ LLM providers (Azure, Gemini, Bedrock, Anthropic, OpenAI, etc.)
- Real‑time spend tracking, budget enforcement, and rate‑limit controls per team or user
- Automatic model fallback and load‑balancing to maintain service continuity
- Integrated observability with logging to Langfuse, Arize Phoenix, Langsmith, and OTEL
- Security features including virtual API keys, JWT auth, SSO, and audit logs (enterprise)
- Prompt management, batch request handling, and S3 logging for compliance
- Deployable as Docker container for on‑premises use or as a managed cloud service