How to stop an agent from overspending on APIs

1. Why this guide matters

Runaway API spend is one of the first real incidents agent teams hit. It rarely looks dramatic at first. It just accumulates quietly until you wish you had a policy checkpoint.

This pattern forces each billable call through NORNR so you get a yes, queue or reject decision before the spend lands.

2. Install what you need

pip install agentpay

This guide uses the hosted NORNR path at https://nornr.com, so you can validate the decision flow without standing up the full local stack first.

3. Create the governed wallet

from agentpay import Wallet

wallet = Wallet.create(
    owner="api-agent",
    daily_limit=35,
    require_approval_above=10,
    base_url="https://nornr.com",
)

This wallet is the mandate. It sets the budget and review threshold before the framework-specific workflow is allowed to continue.

4. Apply it in the workflow

for task in tasks:
    decision = wallet.pay(amount=4.00, to="openai", purpose="model call")
    if decision.get("status") != "approved":
        print("Stop further API calls.", decision)
        break
    run_model_call(task)

The key pattern stays the same across frameworks: ask NORNR for a decision first, then let the expensive or externally billable step run only if policy says yes.

5. What to expect

• approved means the workflow can continue immediately inside its mandate.
• queued means the request crossed an approval threshold and should wait for review.
• rejected means policy did not allow the action to proceed.

That three-way split is what makes the pattern useful: low-risk work stays fast, higher-risk work becomes reviewable, and clearly out-of-policy work never leaves the workflow.

6. Where to go next

• Hosted quickstart
• Control room
• Guides library