Skip to main content

Documentation Index

Fetch the complete documentation index at: https://braintrust.dev/docs/llms.txt

Use this file to discover all available pages before exploring further.

LiteLLM is a unified interface for calling 100+ LLM APIs using the OpenAI format. Braintrust automatically traces LiteLLM calls across all providers including OpenAI, Azure, Anthropic, Cohere, Replicate, and more.
This guide covers manual instrumentation. For quicker setup, use auto-instrumentation.

​
Setup

Install LiteLLM alongside the Braintrust SDK: 
// uv
uv add braintrust litellm
// pip
pip install braintrust litellm

​
Trace with LiteLLM

Braintrust provides a patch function that automatically instruments LiteLLM to capture all model interactions. braintrust.auto_instrument() patches LiteLLM automatically. See Trace LLM calls for details about auto-instrumentation. Call patch_litellm() before importing LiteLLM to enable automatic tracing:
trace-litellm.py
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 are 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:
  • Chat and text completion / acompletion calls across different providers
  • Audio speech (speech / aspeech) calls, with the generated audio captured as an Attachment
  • Audio transcription (transcription / atranscription) calls
  • Image generation (image_generation / aimage_generation) calls
  • Request and response data
  • Token usage and costs
  • Latency metrics
  • Error tracking

​
Resources