How to Analyze Your Claude Bill

👋 Hi, it’s CJ Gustafson and welcome to Mostly Metrics.

Are you ready to save money on tokens?

I’ve had multiple CFOs and FP&A pros come to me and say something along the lines of

❝

“I have no idea what I’m looking at when I get an Anthropic invoice.

I just know it’s going up.”

This is the start of a two part series on managing LLM token costs. All parts will be recorded on video, accompanied by the source files and final outputs.

  • Part 1: How to Audit Your AI Bill for Savings (this one)

  • Part 2: How to budget for token costs internally

Upgrade to paid today so you can get the entire series.

Upgrade

In today’s tutorial we start with a real Anthropic invoice + a data export with usage by model.

By the end of today’s tutorial you’ll be able to:

  1. Catch a legacy model you're overpaying for

  2. Tell when caching is off and costing you.

  3. Move overnight work to the cheap lane.

  4. Right-size the model to the job.

  5. Read your effective rate and concentration.

Below the line, paid readers get:

  • The full build video, start to finish

  • Every prompt, copy-paste ready

  • The sample invoice and usage export

  • The one-page monthly checklist

You’ll have everything to run this on your own bill by the end.

logo

Subscribe to our premium content to read the rest.

Become a paying subscriber to get access to this post and other subscriber-only content.

Upgrade

Your subscription unlocks:

  • In-depth “how to” playbooks trusted by the most successful CFOs in the world
  • Exclusive access to our private company financial benchmarks
  • Support a writer sharing +30,000 hours of on-the-job insights

Keep Reading