# LunaRoute — guides/how-much-concurrency

Markdown twin for https://www.lunaroute.com/guides/how-much-concurrency/ — canonical HTML at https://www.lunaroute.com/guides/how-much-concurrency/.


<div class="pricing-guide-intro">

Count the model calls you have running at the same moment on a busy day, not the number of tools or users. One Claude Code session usually needs one. Every subagent or extra session running in parallel needs one more. Work that can wait should go to the background tier, where it doesn't use your priority slots. Then pick the plan whose number of priority concurrent requests covers that peak.

</div>

<section class="pricing-guide-glance" id="sizing-plans">

## Quick sizing by workload

<table class="pricing-guide-table sizing-guide-table" role="table">
<caption class="sr-only">Plan sizing by workload</caption>
<thead role="rowgroup">
<tr role="row"><th scope="col" role="columnheader">Plan</th><th scope="col" role="columnheader">Concurrent capacity</th><th scope="col" role="columnheader">Price per month</th><th scope="col" role="columnheader">Fits when you run at most</th></tr>
</thead>
<tbody role="rowgroup">
<tr role="row"><th scope="row" role="rowheader">Personal Agent</th><td role="cell" data-label="Concurrent capacity">1, scheduled as capacity becomes available; no priority scheduling</td><td role="cell" data-label="Price per month">$19.99</td><td role="cell" data-label="Fits when you run at most">One personal agent (OpenClaw, Hermes) handling your tasks</td></tr>
<tr role="row"><th scope="row" role="rowheader">Pro</th><td role="cell" data-label="Concurrent capacity">2 priority</td><td role="cell" data-label="Price per month">$99</td><td role="cell" data-label="Fits when you run at most">One Claude Code session, plus an occasional second session or subagent</td></tr>
<tr role="row"><th scope="row" role="rowheader">Max</th><td role="cell" data-label="Concurrent capacity">4 priority</td><td role="cell" data-label="Price per month">$199.99</td><td role="cell" data-label="Fits when you run at most">Up to 4 sessions or subagents working at the same time</td></tr>
<tr role="row"><th scope="row" role="rowheader">Apex</th><td role="cell" data-label="Concurrent capacity">6 priority</td><td role="cell" data-label="Price per month">$299</td><td role="cell" data-label="Fits when you run at most">Up to 6 agents at the same time, with batch work on the background tier</td></tr>
<tr role="row"><th scope="row" role="rowheader">Teams</th><td role="cell" data-label="Concurrent capacity">10 priority, plus bundles of 10</td><td role="cell" data-label="Price per month">$499.99, plus $499.99 per bundle</td><td role="cell" data-label="Fits when you run at most">Your team's peak across everyone, with per-member limits</td></tr>
</tbody>
</table>
<p class="pricing-guide-table-note">Every coding plan also includes overflow capacity, so a short spike above your priority number can run at lower priority when capacity is available. Queue limits and timeouts still apply.</p>

</section>

<div class="pricing-guide-reading">
<nav class="pricing-guide-contents" aria-label="In this guide">
<p>In this guide</p>
<ul>
<li><a href="#sizing-plans">Plan sizing</a></li>
<li><a href="#request-count">What counts</a></li>
<li><a href="#common-setups">Common setups</a></li>
<li><a href="#need-more">When to add capacity</a></li>
<li><a href="#our-suggestion">Our suggestion</a></li>
<li><a href="#sizing-faq">FAQ</a></li>
</ul>
</nav>
<div class="pricing-guide-copy">
<section id="request-count">

## What counts as a concurrent request

A concurrent request is one model call that's running right now. It starts when the request reaches the model and ends when the response finishes. Requests waiting in a queue don't count, and neither does the time an agent spends running tests, editing files or waiting for you.

That's why a single developer rarely needs as many slots as they expect. An agent spends a lot of its time doing things other than calling the model.

</section>

<section id="common-setups">

## Common setups

### Claude Code, one session.

Claude Code mostly makes one model call at a time, so one session uses one concurrent request while it's thinking. Pro gives you a second slot for a quick parallel session or a burst of subagents. See [Using Claude Code with LunaRoute](/claude-code/).

### Claude Code with subagents.

When Claude Code fans a task out to subagents, each one running in parallel holds a slot while it generates. If you regularly have up to four running at once, Max fits.

### Several sessions or worktrees.

Running one agent per branch is where concurrency adds up fastest. Count the sessions you typically have working at the same time. People rarely have all of them calling the model at once, so the peak is usually lower than the number of open terminals.

### Batch and background jobs.

Document processing, evaluations and overnight runs don't need priority. Add `-background` to the model name (for example, `glm-5.3-background`) and those requests fill gaps around your interactive work instead of competing with it. They can wait up to 240 seconds for a slot ([concurrency docs](https://docs.lunaroute.com/concepts/lanes/)).

### Teams.

Size Teams for the team's busiest hour, not for the number of people. Admins can cap each member's concurrency from the Members page, so one person's batch job can't take the whole pool. Add capacity in bundles of 10 priority requests as you grow.

</section>

<section id="need-more">

## How to tell if you need more

See also https://www.lunaroute.com/llms.txt and https://www.lunaroute.com/openapi.json
