Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. Our OpenAI and Claude Bills Keep Growing, but We Can't Tell Which Feature or Customer Is Driving Them. How Do We Find Out?
Problems We Solve

Our OpenAI and Claude Bills Keep Growing, but We Can't Tell Which Feature or Customer Is Driving Them. How Do We Find Out?

AI bill rising and no idea which feature or customer drives it? How SpiderHunts adds AI cost observability, tracing spend per feature, customer and prompt.

Updated 3 min readBy SpiderHunts Technologies

Free estimateNo obligation

Get a free estimate

Tell us what you need. A senior engineer reads every enquiry.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →

Quick answer — TL;DR

An AI bill you cannot break down is usually a logging gap: requests go to OpenAI or Anthropic with no record of which feature, customer or prompt version sent them. SpiderHunts routes AI calls through a thin layer that records tokens, model, cost, feature and customer for every request, then builds dashboards and alerts on top, so you can see what drives spend and fix the expensive parts.

One number on an invoice

The AI features went live and people like them: a support assistant, document summaries, a search that understands questions. The provider's invoice arrives each month as a single number, and it has been climbing. The dashboard shows usage by day and by model, perhaps by API key. It does not tell you that most of the spend comes from one feature, or one customer, or one prompt that quietly got longer.

Finance asks whether the AI features pay for themselves. Product asks whether to include them in the cheaper plan. Nobody can answer with numbers.

Why AI spend is hard to see

  • Several features share one API key, so the provider cannot separate them.
  • Costs depend on tokens, not requests, and token counts vary with prompt length, retrieved context and conversation history.
  • Background jobs, retries and agent loops make calls nobody sees in the interface.
  • Prompt changes that add instructions or context raise the cost of every call from that point on.
  • Different models have very different prices, and it is not always clear which one each feature uses.

The underlying issue is that AI calls are treated like any other API call, when each one carries a variable price. Without recording the context of each call, the bill cannot be explained after the fact.

What not knowing costs

ProblemConsequence
No cost per featureYou cannot tell which features earn their keep
No cost per customerHeavy users on flat plans can make accounts unprofitable
No cost per prompt versionA prompt change that doubles context goes unnoticed
No alertsA runaway loop or abuse is found on the invoice
Guesswork pricingPlans are priced without knowing what they cost to serve

The runaway case is the one that hurts suddenly. An agent stuck in a retry loop or a scraper hitting your chatbot can generate a large bill before anyone looks.

How we make AI costs visible

  1. Route every AI call through one place. A small internal layer (or a gateway such as LiteLLM or a provider's own tooling) handles calls to OpenAI, Anthropic Claude, Azure OpenAI or other models.
  2. Record context with every call: feature, customer or account, user, model, prompt version, input and output tokens, cached tokens, latency and calculated cost.
  3. Send that data to a store you can query, alongside your other application logs, or to an LLM observability tool such as Langfuse or Helicone where that suits you.
  4. Build dashboards for the questions people actually ask: cost per feature, per customer, per plan and per prompt version over time.
  5. Set alerts and limits: spend thresholds per day, per customer and per feature, and caps on agent loops and retries.
  6. Use the data to reduce cost where it makes sense: trimming context, caching repeated answers, using smaller models for simple steps, and batching work that does not need an instant reply.

We keep personal data out of these logs where it is not needed, storing token counts and metadata rather than full prompts unless you have decided otherwise and have a reason to.

With costs traced

You can see which feature and which customers drive spend, and how that changes when a prompt or model changes. Pricing decisions are based on the real cost to serve. An unusual spike raises an alert on the day it starts. And cost reductions are aimed at the calls that matter instead of general belt-tightening.

Does this match your situation?

  • Your AI provider bill has grown and you cannot say why.
  • Several features or products share one API key.
  • You do not know what an average customer costs in AI usage.
  • Nobody would be alerted if AI spend jumped overnight.
  • You are deciding how to price AI features without cost data.

FAQ

Frequently asked questions

The questions readers ask us after this guide.

Still have a question?

Ask us directly — a senior engineer will get back to you.

Ask about your project

Is the provider's usage dashboard not enough?

It shows totals by model and key. It cannot show feature, customer or prompt version unless you record that yourself, which is what this setup adds.

Will adding a logging layer slow responses down?

Recording metadata adds very little overhead when done asynchronously. The call to the model itself takes far longer.

Does this work across several AI providers?

Yes. Routing all calls through one layer gives you consistent records whichever provider or model handles the request.

Do we have to log the full prompts?

No. Token counts and metadata are enough for cost tracking. Logging full prompts is a separate decision with privacy implications.

Keep reading

More on Problems We Solve

Start here

AI spend you cannot explain?

Tell us which AI providers you use, what features call them and how you see costs today. We will suggest how to trace spend to features and customers, and if your provider's dashboard is enough, we will say so.

  1. You tell us what you needTwo minutes on the form, or a message on WhatsApp.
  2. A senior engineer reviews itAnd comes back with questions, a realistic range and an honest view on fit.
  3. Free 30-minute scoping callWe talk through scope, options and a realistic estimate — with no obligation.
Free estimateNo obligation

Talk to someone who builds this

Send a short brief and we will come back with an honest view and a realistic range.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →