Skip to main content

Overview

LiteLLM is a framework/library for building LLM applications that simplifies accessing many models across different providers.

Default configuration

1

Ensure you have the latest version of Laminar

2

Initialize Laminar

Laminar auto-instruments LiteLLM. No callback is required.
LaminarLiteLLMCallback is deprecated and does nothing. Remove it if you already use it.
3

Run your code and see traces in Laminar

Example code:
LiteLLM trace

OpenAI

Trace the OpenAI SDK directly in TypeScript and Python.

Anthropic

Trace the Anthropic SDK directly in TypeScript and Python.

OpenRouter

Trace OpenRouter requests with model and cost attribution.

Cohere

Trace Cohere chat, embed, and rerank calls.

LangChain / LangGraph

Trace LangChain chains and LangGraph graphs.

All integrations

Browse every provider, framework, coding agent, and browser integration Laminar supports.