Credits, provider billing, and run review

Home Tools Platforms Make Credits, provider billing, and run review

Track scenario usage and model-provider usage as different parts of operating cost.

Workflow & automation · Documented · Documentation checked 2026-10-04

Make scenarios and Make AI Agents (New); connected model providers have their own terms.

Scenario limits vary by plan. AI Agents (New) is in open beta; custom AI providers require a paid plan.

The worked example is illustrative and has not been tested in a signed-in product account.

What it does and how it connects

Track scenario usage and model-provider usage as different parts of operating cost.

Make uses credits as its billing unit, while operations describe module activity. AI usage can have dynamic components. With a custom provider, provider token billing and Make usage are separate; built-in provider paths account for usage differently.

Walkthrough

Use the product named in the access panel. The steps below combine documented controls with the editorial example.

  1. Identify the scenario’s modules and connection types.
  2. Run a small controlled sample and inspect recorded usage and execution metadata.
  3. Estimate expected frequency, input size, and potential tool-call repetition.
  4. Set appropriate plan / provider budgets and a review cadence before increasing volume.

Worked example

Compare a fixed classification step with a tool-using FAQ agent on the same synthetic input. The purpose is to inspect actual run usage, not to claim that one is universally cheaper. Include both platform and external-provider charges where applicable.

Illustrative operating record
Run ID and input count
Modules / tool calls used
Recorded Make credits
External provider usage if applicable
Output quality and review time
Failure / retry count
Stop expansion when budget, quality, or exception handling is unresolved

Inspect and verify the result

Use actual account records rather than an invented token estimate. Check repeated tools, failed runs, and retries. Include human review time when deciding whether the process is worthwhile.

Limits and troubleshooting

Long inputs and variable agent loops can change cost. Old tutorials may use operations as the billing term. A single successful run is not a reliable estimate for a mixed workload.

Data, permissions, and actions

Usage logs can include task and account information. Budget settings do not replace data or permission controls. Give an operator responsibility for pausing schedules, removing unnecessary tools, and reviewing exceptions.

Scenarios, modules, and mapped data

Move records through a fixed scenario and inspect which values each module receives.

Explore Scenarios, modules, and mapped data

Fixed AI triage with a review filter

Classify synthetic requests while keeping authoritative review separate from AI output.

Explore Fixed AI triage with a review filter

A bounded beta knowledge agent

Use the beta agent to retrieve approved workshop evidence and produce a validated response draft.

Explore A bounded beta knowledge agent

Permissions and meaningful approvals

Decide what a system may read, what it may change, and when someone needs to authorize a concrete action.

Explore Permissions and meaningful approvals

Sources and verification

Documentation checked 2026-10-04. Examples are illustrative unless described otherwise.

Credits and provider billing · Make

Make AI Agents (New) configuration · Make

Share this page