My LLM Bill Kept Growing, but User Traffic Didn’t

My request count looked normal. Traffic was mostly flat. There was no sudden wave of new users, no...

venerdì 10 luglio 2026 New tab

1,567 words~7 min read

My request count looked normal.

Traffic was mostly flat. There was no sudden wave of new users, no runaway background job, and no obvious model upgrade hiding in a deployment.

But the LLM bill kept climbing.

My first instinct was to look for the usual suspects: a pricing change, an expensive model accidentally pushed to production, or someone hammering an endpoint.

None of those explanations held up.

My LLM Bill Kept Growing, but User Traffic Didn’t

My LLM Bill Kept Growing, but User Traffic Didn’t

Related reading

7 things I learned trying to stop LLM API bills from silently exploding

5 Things Your LLM Bill Is Hiding From You (And How to Find Them)

How I Cut LLM API Costs by 60% With 2 Lines of Code

I Cut My LLM Bill 40x: A Backend Engineer's Migration Notes

My LLM API Calls Were Failing Silently. Here's the Logging Setup I Wish I Had…

Five ways your LLM cost tracking is lying to you

Related reading

7 things I learned trying to stop LLM API bills from silently exploding

5 Things Your LLM Bill Is Hiding From You (And How to Find Them)

How I Cut LLM API Costs by 60% With 2 Lines of Code

I Cut My LLM Bill 40x: A Backend Engineer's Migration Notes

My LLM API Calls Were Failing Silently. Here's the Logging Setup I Wish I Had…

Five ways your LLM cost tracking is lying to you