LLM Observability for LiteLLM

Overview

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

Default configuration

Ensure you have the latest version of Laminar

pip install -U 'lmnr[all]'

Initialize Laminar

Laminar auto-instruments LiteLLM. No callback is required.

import os
import litellm
from lmnr import Laminar

Laminar.initialize(project_api_key=os.environ["LMNR_PROJECT_API_KEY"])

LaminarLiteLLMCallback is deprecated and does nothing. Remove it if you already use it.

Run your code and see traces in Laminar

Example code:

import os
import litellm
from lmnr import Laminar

Laminar.initialize(project_api_key=os.environ["LMNR_PROJECT_API_KEY"])

response = litellm.completion(
    model="gpt-5-nano",
    messages=[
      {"role": "user", "content": "What is the capital of France?"}
    ],
)

deepagents Langfuse

Overview

Tracing

Signals

Debugger

Evaluations

Datasets

Platform

Overview

Default configuration

​Overview

​Default configuration

Overview

Default configuration