Conto

Micropayments

Budgets for machine payments

Cap each request and session so API, inference, and compute spend stays bounded.

Industries

Compute & AI infra · Agentic commerce

Best for

Inference, APIs, service spend

Controls

Per-call caps, session budgets, velocity

Outcome

Machine-speed buying with hard limits

How per-call spend stays inside budget

Budget at request time

$4.12/ $5.00 session

82% spent · $0.88 left

Per-call cap$0.50
Velocity18 / 60 per min

Per-call decisions

inference.helia.dev$0.012
search.serp.api$0.040
gpu-rent.xyz$1.20
embeddings.io$0.008
render.farm$0.95
over per-call cap session budget spent

Every paid request is checked before the provider is paid. Low-cost calls keep flowing, while an oversized call or an exhausted session both stop without a human in the loop.

Case Study

Enchant: x402 and MPP in action

Enchant uses Conto to apply budgets and approvals to x402 and MPP payments. Try it free and get signup credits.

Visit Enchant at askenchant.com

Prompt

User asks Enchant

A task can require a paid tool, data source, or model call.

Quote

Price appears first

The paid step shows its cost before anything runs.

Control

Conto checks policy

Budgets, per-call caps, and approvals are evaluated before spend.

Payment

x402 or MPP clears

Approved micropayments settle and update the user budget.

Payment flow

x402 and MPP micropayments

Spend layer

Conto budgets for every user

Control point

Policy before each paid request clears

Service-spend activity with budget context attached

Machine-speed payments show up with the same context as enterprise approvals and budgets, which makes service-spend automation easier to govern alongside the rest of the payment estate.

Evaluationpol_4f9c · 142ms

Payment request

procurement-agent → Quill Data$8,500.00
quilldata.io · datanew counterparty

Rules evaluated

Per-transaction limit
$8,500 ≤ $10,000pass
Monthly budget
$24.1k / $40kpass
Counterparty trust ≥ 70
new · no score yetreview
Category allowlist
datapass

Routed to review

1 of 4 rules needs a human before settlement.

policy: procurement-spend-v4

Controls that bound automated service spend

Per-call, session, provider, and velocity policies stop runaway spend without forcing every low-cost request into manual review.

Per-call ceilings

Prevent a single API or inference request from blowing past the allowed unit economics for the task.

Session envelopes

Give each task or agent run a hard budget so many small calls cannot add up to an unlimited bill.

Provider-level policy

Restrict autonomous spend to the providers or service types you actually trust for the workflow.

Velocity monitoring

Catch broken loops or runaway retry behavior before the agent can hammer a paid endpoint continuously.

How per-call payments stay inside budget

Agents can buy APIs, inference, and compute on demand while Conto checks unit economics and task budgets before each paid request.

Step 1

The agent chooses a paid service

A compute or API workflow selects the service endpoint and proposes the call based on price, latency, or task fit.

Step 2

Conto checks call-level economics

Conto checks each request against your per-call limits, session budgets, and provider rules before the service is paid.

Step 3

Normal usage continues until budget is spent

Low-cost calls keep flowing. Expensive routes or exhausted budgets are blocked before the provider is paid.

Demo

Watch per-call payments stay inside a session budget

A buyer agent selects inference providers call by call. Per-request ceilings, session budgets, and velocity checks keep low-cost usage flowing and block spend that exceeds the task envelope.

Pay-per-call inference with hard session budgets

An AI shopper that can only spend where you let it

Machine payments that stay in budget

Engineering teams can let agents buy services dynamically without accepting unbounded cost exposure.

The same control plane works for per-call infrastructure spend and more traditional payouts.

Every paid request comes with a budget story that finance can understand.