openinference-instrumentation-litellm
OpenInference liteLLM Instrumentation
Decision gist · record as of 2026-08-14
Yes, if you use LiteLLM and need observability. The package is actively maintained, has no known vulnerabilities, installs cleanly with low friction, and is Apache-licensed. It solves a real problem—seeing what your LLM calls are actually doing—with minimal code changes. Install it alongside an OpenTelemetry collector (Phoenix, AX, or your own) to get immediate tracing.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; LiteLLM and an OpenTelemetry exporter (e.g., Arize Phoenix) must be installed separately to actually collect and view traces.
- Low friction: pure Python wheel with seven runtime dependencies, all standard observability libraries (opentelemetry-sdk, opentelemetry-instrumentation, openinference packages).
- Active maintenance with a release 2 days old and no known vulnerabilities.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license; you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.
last release 2026-08-12 (2 days) · last repo commit 2026-08-14 · 1,147 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 468,654 downloads/mo, #6,492 on PyPI
Alternatives
Verify before relying
pip install openinference-instrumentation-litellm
from openinference.instrumentation.litellm import LiteLLMInstrumentor
from opentelemetry.sdk.trace import TracerProvider
tracer_provider = TracerProvider()
LiteLLMInstrumentor().instrument(tracer_provider=tracer_provider)- Whether instrumentation overhead is negligible for high-volume LLM call scenarios.
- Support status for LiteLLM Proxy beyond the documented 100+ LLMs.
- Compatibility with custom LiteLLM provider implementations.
What it is and what it does
This package wraps LiteLLM's core functions—completion, embedding, image generation, and Anthropic API calls—to automatically emit structured OpenTelemetry spans. It lets you see detailed traces of every LLM API call your application makes, including inputs, outputs, latency, and errors, without modifying your LiteLLM code.
You install it, instantiate LiteLLMInstrumentor, point it at a TracerProvider connected to an OpenTelemetry collector (like Arize Phoenix), and call instrument(). From that moment on, all instrumented LiteLLM functions emit traces. The package depends on opentelemetry-sdk, opentelemetry-instrumentation, and openinference-instrumentation to handle the tracing plumbing, and uses wrapt to hook into LiteLLM's function calls.
Use it for
- Debug LLM application behavior by viewing detailed traces of completion calls, embeddings, and image generation in Arize Phoenix or similar collectors.
- Monitor production LLM services to track latency, error rates, and API usage across multiple LLM providers via OpenTelemetry exporters.
- Correlate LLM calls with application-level traces to understand end-to-end request flow in complex systems.
- Audit and log all LLM API interactions for compliance or troubleshooting without modifying existing LiteLLM code.
- Analyze Anthropic API call patterns and performance when using LiteLLM's Anthropic wrapper methods.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you use LiteLLM and need observability.
The package is actively maintained, has no known vulnerabilities, installs cleanly with low friction, and is Apache-licensed. It solves a real problem—seeing what your LLM calls are actually doing—with minimal code changes. Install it alongside an OpenTelemetry collector (Phoenix, AX, or your own) to get immediate tracing.
Install
openinference-instrumentation-litellm on PyPI
Before you install
Low friction: pure Python wheel with seven runtime dependencies, all standard observability libraries (opentelemetry-sdk, opentelemetry-instrumentation, openinference packages). Active maintenance with a release 2 days old and no known vulnerabilities.
Requires Python 3.10 or later; LiteLLM and an OpenTelemetry exporter (e.g., Arize Phoenix) must be installed separately to actually collect and view traces.
License in practice
Apache-2.0 permissive license; you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.
Quickstart
pip install openinference-instrumentation-litellm
from openinference.instrumentation.litellm import LiteLLMInstrumentor
from opentelemetry.sdk.trace import TracerProvider
tracer_provider = TracerProvider()
LiteLLMInstrumentor().instrument(tracer_provider=tracer_provider)Verify before relying
- Whether instrumentation overhead is negligible for high-volume LLM call scenarios.
- Support status for LiteLLM Proxy beyond the documented 100+ LLMs.
- Compatibility with custom LiteLLM provider implementations.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <3.15,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagesopeninference-instrumentationopeninference-semantic-conventionsopentelemetry-apiopentelemetry-instrumentationopentelemetry-sdksetuptoolswrapt |
| Maintenance | Actively maintained 2 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 468,654 / month, #6,492 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: openinference_instrumentation_litellm-0.1.37-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “litellm tracing instrumentation”
- openinference-instrumentation-litellmAuto-instruments LiteLLM function calls (completion, embedding, image…
- opentelemetry-instrumentation-litellmAdds OpenTelemetry tracing to LiteLLM, capturing LLM prompts,…
- opentelemetry-instrumentation-pymemcacheAdds OpenTelemetry tracing instrumentation to pymemcache client…
Give your agent the search over MCP, or paste the wish link into any chat.
More Monitoring packages
Wraps any iterable to display a real-time progress bar in the terminal or Jupyter notebook, showing iteration count, elapsed time, and estimated time remaining.
Provides generated Python code for OpenTelemetry semantic conventions, enabling standardized attribute naming and constant definitions for instrumentation and telemetry collection.
Install it if you are using OpenTelemetry and want to follow semantic conventions correctly.
Provides the reference implementation of the OpenTelemetry API for collecting and exporting traces, metrics, and logs from Python applications.
Provides the abstract API and interfaces for OpenTelemetry instrumentation in Python, defining how to emit traces, metrics, and logs without tying code to a specific SDK implementation.
Exports OpenTelemetry observability data to an OpenTelemetry Collector using Protobuf-encoded messages over HTTP.
Install it if you are using OpenTelemetry in Python and need to send data to a Collector over HTTP.
Provides automatic instrumentation commands and programmatic APIs to inject distributed tracing into Python applications without code changes, detecting and instrumenting packages used by your program.
Install it if you need distributed tracing without code changes and have compatible instrumented packages in your environment.
See also openinference-instrumentation-google-genai · openinference-instrumentation-llama-index · arize · openinference-instrumentation-anthropic · openinference-instrumentation-haystack · openinference-instrumentation-openai · openinference-semantic-conventions · arize-otel · arize-phoenix · openinference-instrumentation-agno