---
id: opentelemetry-instrumentation-together
version: "0.62.3"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# opentelemetry-instrumentation-together — OpenTelemetry Together AI instrumentation

License: permissive · Maintenance: active · Downloads: 6.8M/mo

## What it is and what it does

This package hooks into the official Together AI Python library to automatically capture telemetry data from API calls. It wraps Together AI requests and records prompts, completions, and embeddings as attributes in OpenTelemetry spans, integrating with your existing observability infrastructure.

By default it logs all content to spans for visibility into LLM application behavior, but you can disable this via the TRACELOOP_TRACE_CONTENT environment variable if you need to protect sensitive user data or reduce trace size. It depends on the core OpenTelemetry instrumentation framework and semantic conventions for AI workloads.

Use it for:

- Debug Together AI API calls by inspecting prompts and responses in your trace backend.
- Monitor LLM application performance and latency across Together AI endpoints.
- Correlate Together AI requests with other application traces for end-to-end observability.
- Evaluate output quality by reviewing completions captured in span attributes.
- Reduce trace verbosity in production by disabling content logging while keeping call metrics.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Automatically traces calls to Together AI's API endpoints by instrumenting the official Together AI Library, capturing prompts, completions, and embeddings as OpenTelemetry span attributes.

Yes, if you use Together AI and already have OpenTelemetry instrumentation in place. The package is actively maintained, has no known vulnerabilities, and low install friction. It directly solves the problem of observing Together AI API calls within an OpenTelemetry-based system. Be aware that content logging is on by default—set TRACELOOP_TRACE_CONTENT=false if you handle sensitive data.

## Install

pip install opentelemetry-instrumentation-together
uv add opentelemetry-instrumentation-together
poetry add opentelemetry-instrumentation-together

## Installing opentelemetry-instrumentation-together

Before you install: Low install friction with a pure-Python wheel and four runtime dependencies, all within the OpenTelemetry ecosystem. Active maintenance with a recent release.

License in practice: Apache-2.0 permissive license allows use in commercial and proprietary projects with minimal restrictions.

Quickstart:

pip install opentelemetry-instrumentation-together

from opentelemetry.instrumentation.together import TogetherAiInstrumentor

TogetherAiInstrumentor().instrument()

Requires Python 3.10 or later. Requires an active OpenTelemetry SDK and exporter already configured in your application.

Verify before relying:

- Whether the package works with all Together AI API endpoints or only a subset.
- Performance overhead of instrumentation on production workloads.
- Compatibility with specific OpenTelemetry exporter backends.

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 6.8M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

opentelemetry instrumentation llm, together ai tracing, llm api observability, opentelemetry ai monitoring, trace together ai calls, llm span instrumentation, ai api debugging traces, observability, llm-tracing, ai-monitoring

[View on SkillFed](https://skillfed.io/packages/opentelemetry-instrumentation-together) · [View on PyPI](https://pypi.org/project/opentelemetry-instrumentation-together/)