> ## Documentation Index
> Fetch the complete documentation index at: https://help.clinikehr.com/llms.txt
> Use this file to discover all available pages before exploring further.

# How agent credits are used

> What spends an agent credit, how many your plan grants each month, and how to top up without being surprised by a schedule.

export const Path = ({steps = []}) => <span className="ck-path">
    {steps.map((s, i) => <span key={i} className="ck-path__step">
        {i > 0 ? <span className="ck-path__sep" aria-hidden="true">
            ›
          </span> : null}
        {s}
      </span>)}
  </span>;

export const Availability = ({editions = ['all'], plans, roles, note}) => {
  const list = editions.includes('all') ? ['clinic', 'pharmacy', 'lims'] : editions;
  return <div className="ck-avail" role="note" aria-label="Feature availability">
      <span className="ck-avail__label">Available in</span>

      {list.map(e => <span key={e} className={`ck-pill ck-pill--${e}`}>
          {EDITION_LABELS[e] || e}
        </span>)}

      {plans ? <span className="ck-avail__label">Plan</span> : null}
      {plans ? <span className="ck-pill ck-pill--plan">{plans}</span> : null}

      {roles ? <span className="ck-avail__label">Who</span> : null}
      {roles ? <span className="ck-pill ck-pill--role">{roles}</span> : null}

      {note ? <span className="ck-avail__note">{note}</span> : null}
    </div>;
};

<Availability editions={['clinic', 'pharmacy']} plans="Every plan gets a monthly allowance; refill packs are on sale to all" />

Agent credits are what your AI agents spend when they run. Your plan grants a fresh allowance every month, and you can buy refill packs on top. Building agents costs nothing — only running them does.

<Path steps={['Sidebar', 'AI Agents']} />

The **Agent credits** card at the top of the **Agent Builder** page shows your balance, a **Top up** button, and a **Recent activity** list of the last few grants, refills and runs.

## What spends a credit

Two nodes, and only two: **Agent** and **Classify**. Everything else on the canvas — **File search**, **Guardrails**, **MCP**, **If / else**, **While**, **User approval**, **Transform**, **Set state**, **End**, **Note** — costs nothing at all.

That makes the cost of a workflow easy to read off the canvas: count the **Agent** and **Classify** nodes a run will actually pass through. A branch the run does not take costs nothing.

## Your monthly allowance

Clinic & Hospital plans grant, per month:

| Plan      | Monthly agent credits |
| --------- | --------------------- |
| Free      | 50                    |
| Starter   | 1,000                 |
| Essential | 2,500                 |
| Team      | 5,000                 |

## The two rules that decide what gets spent

1. **Monthly plan credits are always spent first.** Refill packs are only touched once the month's allowance runs out.
2. **Refill packs never expire.** An unused pack carries over indefinitely, so buying ahead of a busy period is never wasted.

## A schedule multiplies everything

This is where a small workflow becomes a large bill. The same two-step agent costs wildly different amounts depending on what starts it:

| Trigger                                     | Runs per month | Billable steps per run | Credit-consuming steps per month |
| ------------------------------------------- | -------------- | ---------------------- | -------------------------------- |
| **Manual / Preview**, run a few times a day | \~90           | 2                      | \~180                            |
| **Every day**                               | \~30           | 2                      | \~60                             |
| **Every hour**                              | \~730          | 2                      | \~1,460                          |
| **Every 15 minutes**                        | \~2,920        | 2                      | \~5,840                          |

An **Every 15 minutes** schedule on a two-step agent will exhaust a Team allowance on its own — before a second agent has run at all. A **Public UI** is the other multiplier: every visitor message is a run, which is why the abuse caps on [publishing an agent](/platform/ai/publishing-agents) matter.

Sensible habits:

* Use the slowest schedule that still meets the need. Most "overdue" work is fine on **Every day**.
* Do the filtering in free nodes. Let **If / else** decide whether the run is worth an **Agent** step, rather than having the **Agent** step decide there was nothing to do.
* Use **Classify** for sorting and a single **Agent** step for the writing, rather than several **Agent** steps in a row.
* Watch **Recent activity** on the **Agent credits** card for the first few days after deploying anything scheduled.

## Top up

Select **Top up** on the **Agent credits** card. The **Top up agent credits** dialog explains: "Refill packs never expire and are used after your monthly plan credits. You'll complete payment securely on the next screen." Choose a pack and you are taken to checkout.

<Warning>
  Buying a refill pack charges your payment method immediately. Packs are not refundable once the credits land in your balance, so buy the size you will use — they never expire, but they also do not come back.
</Warning>

## When you run out

Runs stop. A scheduled agent simply does not fire, and a public UI stops answering, until either your monthly allowance renews or you top up. Nothing is deleted and nothing needs re-deploying — the agent resumes on its next trigger once there is a balance.

## Related

<Columns cols={2}>
  <Card title="Credits" icon="https://mintcdn.com/clinikehr/nLyvBRumcl1Yk8z3/images/icons/wallet.svg?fit=max&auto=format&n=nLyvBRumcl1Yk8z3&q=85&s=1749f2e326d74e2e0babbb876485b560" href="/platform/plans/credits" width="24" height="24" data-path="images/icons/wallet.svg">
    The plans-side view of credits across the platform.
  </Card>

  <Card title="Change your plan" icon="https://mintcdn.com/clinikehr/gjlpJWWKqjyYNRzM/images/icons/arrow-up-right-dots.svg?fit=max&auto=format&n=gjlpJWWKqjyYNRzM&q=85&s=e1a3f2d2814fd41a2cf05e42daf51912" href="/platform/plans/change-plan" width="24" height="24" data-path="images/icons/arrow-up-right-dots.svg">
    A bigger monthly allowance, and higher publishing limits.
  </Card>

  <Card title="Build an AI agent" icon="https://mintcdn.com/clinikehr/nLyvBRumcl1Yk8z3/images/icons/robot.svg?fit=max&auto=format&n=nLyvBRumcl1Yk8z3&q=85&s=4d019f2f70988b5ec97273b307339235" href="/platform/ai/agents" width="24" height="24" data-path="images/icons/robot.svg">
    Which nodes are billable, and how triggers work.
  </Card>

  <Card title="Publish an agent" icon="https://mintcdn.com/clinikehr/gjlpJWWKqjyYNRzM/images/icons/globe.svg?fit=max&auto=format&n=gjlpJWWKqjyYNRzM&q=85&s=80fb437fa57114503e6e15ce57caea44" href="/platform/ai/publishing-agents" width="24" height="24" data-path="images/icons/globe.svg">
    Abuse caps on a public chat assistant.
  </Card>
</Columns>
