OpenTelemetry LiteLLM Instrumentation

This library allows tracing LLM prompts and completions sent with LiteLLM. Because LiteLLM normalizes every provider's reply into an OpenAI-style ModelResponse — including custom providers registered via litellm.CustomLLM — a single set of wrappers produces consistent gen_ai.* spans and metrics across all back-ends.

Installation

pip install opentelemetry-instrumentation-litellm

Example usage

from opentelemetry.instrumentation.litellm import LiteLLMInstrumentor

LiteLLMInstrumentor().instrument()

Privacy

By default, this instrumentation logs prompts, completions, and embeddings to span attributes. This gives you a clear visibility into how your LLM application is working, and can make it easy to debug and evaluate the quality of the outputs.

However, you may want to disable this logging for privacy reasons, as they may contain highly sensitive data from your users. You may also simply want to reduce the size of your traces.

To disable logging, set the TRACELOOP_TRACE_CONTENT environment variable to false.

TRACELOOP_TRACE_CONTENT=false