Menu

1 / 4

I loaded 30 days of real LLM traces into a live demo. Here is what they reveal

DEV Community·Adarsh Rao·6 months ago
#GAlcYHL0
#ai#llm#selfhosted#observability#model
Reading 0:00
15s threshold

If you have been building with LLMs, you have probably had one of these moments:

A surprise bill at the end of the month

A model silently returning garbage without an error

No idea which of your services is driving the cost spike

I built Torrix to fix that. A self-hosted LLM observability platform that logs every call, calculates costs token by token, and flags anomalies automatically.

The problem with self-hosted tools : you can't easily try before you install. You need Docker, a server, credentials, 10 minutes of setup. Most people bounce.

So I built a live demo . No signup. No Docker. No installation . Just click and explore.

Here is what's in it.

The setup

The demo loads 30 days of LLM traces across 3 simulated projects:

Production API : GPT-4o and Claude Sonnet handling user requests

Data Pipeline : batch summarisation, GPT-4o-mini doing the heavy lifting

Customer Support Bot : mixed model routing, Haiku for simple queries, Sonnet for complex ones

640 runs. 5 models.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.