Hound your AI bill.
Before it hounds you.
CapHound brings FinOps governance to AI spend. Attribute every dollar to the team, feature, or customer driving it. Enforce budgets in real time. End AI cost surprises at month-end.
No credit card · Up to $5K/mo on the free tier
2 items need triage— click to jump to Open risk signals.
Works with every major AI provider
The Decision Engine in production
Every LLM request flows through CapHound's decision engine.
Block, modify, or allow — recorded with full Access → Budget → Optimization reasoning. Customer-level decisions live in your dashboard; CapHound never aggregates tenant data publicly.
growth-engineering hit its $3,000 monthly cap. Hard block at 429 — caller gets a clear error before any provider charge.
Workspace at 91% of budget. gpt-4o auto-downgraded to gpt-4o-mini for low-stakes traffic.
customer-support-chat within all guardrails. Logged with feature, customer, and team for chargeback.
AI costs don't drift.
They spike.
By the time the invoice arrives, the damage is already done.
Runaway requests, no early warning
A retry loop. A pagination bug. A misconfigured prompt. One mistake fires thousands of API calls before anyone sees it. Your first warning is the invoice.
Silent cost doubling on model swaps
An engineer swaps to a more capable model — for the right reasons. Per-request cost doubles overnight. No alert. No review. Just a bigger bill at month-end.
Spend concentrated in one workflow
70% of your AI bill comes from a single feature or customer. Probably. You can't prove it — there's no per-feature attribution in your provider's dashboard.
Finance asks. Engineering can't answer.
Your CFO sees a $40K AI line item and asks who's spending it. Engineering can't break it down. Both teams lose trust. The bill keeps growing.
Finance sees Product Line.
Engineering sees Service.
The same AI spend, through the right lens for each team. Define the dimensions your business uses — Business Unit, Cost Center, Product Line — and CapHound maps every dollar to them automatically.
Custom dimensions
Go beyond feature and team. Define Business Unit, Product Line, or Cost Center. CapHound rolls up AI spend to match how your finance org thinks about cost — without changing how your engineers tag requests.
Showback & chargeback
Show every team their AI spend at month end. For companies billing back by customer or business unit, export a clean chargeback report in one click — ready for finance, no spreadsheet required.
Automatic tag normalization
Engineers tag inconsistently. “cs-chat”, “customer-support”, and “cust-support-chat” are the same feature. CapHound normalizes the variants into a single canonical value — clean attribution without a tagging mandate.
Dimensions
featureteamcustomerbusiness_unitproduct_lineCost breakdown
Business Unit
AI spend rolled up for finance reporting
Enforce. Attribute. Control.
CapHound doesn't just report on your AI usage — it governs it in real time.
Enforcement
Set hard limits per feature, team, or customer. When the budget hits, CapHound blocks the request. Not an alert — a block.
Attribution
Every request tagged by feature, team, environment, and customer. You know exactly what caused the spike — and who to talk to.
Routing
Define rules. CapHound routes automatically. Dev environments use cheap models. Free users hit the cheaper tier. No app changes.
Every decision,
fully audited.
Watch each request flow through Access, Budget, and Optimization checks. See exactly what was blocked, what was modified, and why — with timestamps and reasoning that finance and engineering can both read.
API key validated
Monthly limit exceeded · $5,000 / $5,000
Pipeline halted at budget
API key validated
Within limit · $4,210 / $5,000
Downgrade rule: env=dev → switch to gpt-4o-mini
API key validated · scope: production
Within customer budget · $1,840 / $5,000
No routing rules matched
Drop in.
Two lines.
CapHound mirrors the OpenAI API exactly. Change two lines of config — your existing code stays the same.
What changes
Two required lines. One optional.
Use your CapHound key
Replace your OpenAI API key with one CapHound generated for your workspace.
api_key="caphound_live_..."Point base_url to CapHound
Your requests now route through us. We forward to OpenAI/Anthropic/Gemini behind the scenes.
base_url="https://api.caphound.ai/v1"Tag with feature (optional)
OptionalAdds attribution metadata so you can break down spend by feature, team, or customer.
extra_headers={"x-caphound-feature": "chat"}That's it. Same SDK calls. Same response shape. Same models. Zero refactor.
Built for
enterprise procurement.
Every workspace is hard-isolated at the database layer. Every budget decision is logged with full context. Finance gets read-only access to chargeback reports. Engineering gets enforcement. Nobody gets what they shouldn't.
SOC2 Type II in progress. Security review available on request.
Put your AI layer
under control.
Start free. Add enforcement as your spend grows. No credit card required.