# Instrument your LLM calls to analyze AI costs and usage

DevFeed: [Instrument your LLM calls to analyze AI costs and usage](<https://devfeed.tech/articles/instrument-your-llm-calls-to-analyze-ai-costs-and-usage-18537.md>)

Original publisher: [Read original article](<https://www.tinybird.co/blog/instrument-your-llm-calls>)

Author: Alberto Romeu, Rafa Moreno

Published: 2025-03-27T00:00:00Z

Content type: tutorial

Language: en

Sources: [Tinybird](<https://devfeed.tech/sources/tinybird.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Latency](<https://devfeed.tech/topics/latency.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-x-data](<https://devfeed.tech/tags/ai-x-data.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [observability](<https://devfeed.tech/tags/observability.md>)

## AI overview

A tutorial on instrumenting LLM calls to analyze AI costs, usage, and latency through an observability setup.

## Source excerpt

Instrument your LLM calls or fly blind on costs and latency. This observability setup shows exactly what your AI is doing.