> ## Documentation Index
> Fetch the complete documentation index at: https://opentracy.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Welcome to OpenTracy
> The auto-distillation layer for your LLM calls — drop in, cut cost, keep quality
## What OpenTracy gives you
Drop OpenTracy in where your OpenAI SDK sits today. Every request becomes a
**trace**. Same-intent traces cluster into a **dataset**. Datasets train a
**distilled student model** that matches your teacher's output on *your*
traffic. The routing layer swaps the student in under your app through an
alias — **your code never changes, your cost curve goes down**.
## Install
```bash theme={null}
pip install opentracy
```
The wheel ships the Go routing engine, the ONNX embedder, and a pre-trained
router — `pip install` and you can route on Linux (x86\_64 / ARM64), macOS
(Apple Silicon), or Windows (x86\_64).
Then jump to the [Quickstart](/quickstart).
## The loop, one step at a time
Point your OpenAI SDK (or any of the 13 providers) at OpenTracy. No code
changes beyond `base_url`.
Prompt, response, model, cost, latency, tokens — persisted to ClickHouse
automatically.
Same-intent traces are grouped and labeled (e.g. "classify support tickets",
"generate SQL").
The teacher (GPT-4o, Sonnet, ...) labels the dataset; a tiny student
(llama-3.2-1b, qwen3-0.6b, ...) fine-tunes to match.
`model="smart"` now resolves to the distilled student. Your app code
never changed.
Five minutes: install, route your first request, see cost + latency metadata.
The full story — request → trace → dataset → student → alias.
What we capture per request, where it lives, how it becomes training data.
Turn your teacher's output on your traffic into a cheap custom student.
## Why OpenTracy exists
Every team running LLMs in production hits the same wall:
* GPT-4o / Claude Sonnet works — but it's **expensive**.
* GPT-4o-mini / Haiku is cheap — but **quality risk is real** on hard prompts.
* Fine-tuning a smaller model is the right answer — but it needs **a dataset
you don't have**, training infrastructure you don't want, and a way to
**actually serve the new model behind your existing code**.
OpenTracy is the four things, glued together: a gateway that turns traffic
into training data, automatic dataset curation, distillation training, and
a routing layer that swaps models behind aliases so your app code doesn't
change on the day the cheap model goes live.
## How this documentation is organized
The "why" — traces, datasets, auto-routing, distillation, and the pipeline that ties them together.
Task-oriented walkthroughs — drop-in OpenAI replacement, self-hosting, Python SDK.
Every function in the Python SDK with arguments, return types, and examples.
Source code, issues, and the CI workflow that ships the wheels.