> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/ai-voice-agents/phone-numbers/concurrent-calls.md).

# Concurrent calls

How many calls your account can have live at once, how that total splits into separate inbound and outbound limits per plan, and how to prepare for a burst of calls.

**Concurrent calls** (concurrency) are the calls your account can have **live at the same time**. Your plan sets a total, and that total is split into **two separate limits**:

* **Inbound**: people calling your agent's number.
* **Outbound**: your agent calling people, sequences included.

Each side has its own limit. A full inbound side does not borrow free outbound spots, and the other way around.

***

## Limits per plan

| Plan           | Total | Inbound | Outbound |
| -------------- | ----- | ------- | -------- |
| **Free**       | 1     | 0       | 1        |
| **Pro**        | 5     | 2       | 3        |
| **Scale-Up**   | 20    | 10      | 10       |
| **Prime**      | 30    | 15      | 15       |
| **Enterprise** | 30    | 15      | 15       |

When one side is full, new calls on that side can't connect until a live call ends. They show as **Concurrency Limit Reached** in your call history.

Concurrency is not the same as sequence pacing. Pacing controls how fast a sequence starts new calls; concurrency caps how many calls are active at once, across your whole account.

{% content-ref url="/pages/8yIUCoPD1oNPbiGLgIRU" %}
[Call Logic & Limits](/ai-voice-agents/how-to-create-your-first-campaign-in-dapta/call-logic-and-limits.md)
{% endcontent-ref %}

***

## Add more capacity

Additional concurrency spots can be added for **$10 USD/month each**. Extra spots add to your total, which is split evenly between inbound and outbound (when the total is odd, the extra spot goes to outbound). To raise your limit, contact support.

***

## Expecting many calls at once?

A live event, a launch or an ad that asks people to call your agent can bring a burst of inbound calls. Before the day:

1. **Have the agent ready at least 48 hours before.**
2. **Estimate how many people will call at the same time** and compare that number with your **inbound** limit, not your total. On Prime or Enterprise, that is 15 calls at once.
3. **Ask support to raise your limit in advance** if your estimate is higher.
4. **Test with several calls at the same time**, not one by one. A single test call does not show what happens when the line fills up.
5. **Have a tested backup**, such as a web call link or a QR code, in case the line is full.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.dapta.ai/ai-voice-agents/phone-numbers/concurrent-calls.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.