LiteLLM

Trace your LiteLLM applications by patching LiteLLM with Braintrust's wrapper.

LiteLLM is a unified interface for calling 100+ LLM APIs using the OpenAI format, supporting providers like OpenAI, Azure, Anthropic, Cohere, Replicate, and more.

Installation

uv add braintrust litellm

Usage

from braintrust.wrappers.litellm import patch_litellm
 
patch_litellm()
 
import litellm
from braintrust import init_logger
 
# Initialize Braintrust
logger = init_logger(project="litellm-example")
 
# Use LiteLLM as normal - all calls will be automatically traced
response = litellm.completion(
    model="gpt-4o-mini", messages=[{"role": "user", "content": "What is the capital of France?"}]
)

This will automatically send all LiteLLM interactions to Braintrust, including:

• Model calls across different providers
• Request and response data
• Token usage and costs
• Latency metrics
• Error tracking

Learn More

• LiteLLM Documentation
• DSPy Integration - Uses LiteLLM tracing plus DSPy-specific callbacks