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

# Concurrency and Scaling

> Agent-call concurrency limits and compute resources for Line voice agents.

## Compute Resources

Each call has access to 1GB memory and 0.5 vCPU. Contact support to increase limits.

<Card title="Contact Support" href="https://cartesia.ai/contact" />

## Concurrency

Concurrent call limits by subscription tier:

| Subscription Tier | Concurrency Limit |
| ----------------- | ----------------- |
| Free              | 8                 |
| Pro               | 12                |
| Startup           | 20                |
| Scale             | 60                |

<Note>
  These limits apply to concurrent Line agent calls—inbound, outbound, and batch. They are separate from [TTS and STT concurrency limits](/use-the-api/concurrency-limits-and-timeouts) and do not share a pool with them, even when the numbers match.
</Note>

<Tip title="Outbound Concurrency" icon="dialpad">
  **Outbound Concurrency**

  When triggering outbound calls, you are limited to triggering one call per second while the overall concurrency limits still apply.
</Tip>