> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). Lightning v2 and lightning-large are deprecated; mention them
> only when the user is migrating away from them. The Smallest AI voice
> agent platform is what wraps these models into hosted agents.

# Concurrency and Limits

> Understanding API concurrency limits and rate limiting

## Overview

Smallest AI API implements concurrency limits to ensure fair usage and optimal performance across all users. Understanding these limits is crucial for building robust applications that integrate with our services.

## What is Concurrency?

**Concurrency** refers to the number of simultaneous requests that can be processed at any given moment. In the context of Smallest AI API:

* **1 TTS request concurrency**: Only 1 Text-to-Speech request can be actively processed at a time per account
* This applies to every Lightning v3.1 TTS endpoint (sync, SSE, WebSocket)

## How Concurrency Works

### HTTP API Requests

* Each HTTP API call (POST request) counts as **1 concurrency unit** while being processed
* Once the request completes and returns a response, the concurrency slot is freed
* If you attempt to make a second HTTP request while one is already being processed, you'll receive a `429 Too Many Requests` error

### WebSocket Connections

* You can establish up to **5 WebSocket connections** simultaneously (5 × concurrency limit)
* However, only **1 concurrent request** can be processed across all WebSocket connections
* Additional requests sent through any WebSocket while one is being processed will be rejected with an error

## Monitoring Your Usage

### Dashboard Monitoring

Check your usage patterns in the Waves dashboard to:

* Monitor request patterns
* Identify peak usage times
* Plan capacity requirements

Link to dashboard: [https://app.smallest.ai/dashboard/developers/usage?utm\_source=documentation\&utm\_medium=api-references](https://app.smallest.ai/dashboard/developers/usage?utm_source=documentation\&utm_medium=api-references)

## Parallel Conversational Bots

For conversational applications, you can potentially support approximately **4x your concurrency limit** in parallel conversations. This is based on the typical speaking patterns where users don't speak continuously.

### How It Works

* **Concurrency limit**: 1 active TTS request
* **Potential parallel conversations**: \~4 conversations simultaneously
* **Reasoning**: In natural conversation, users speak intermittently with pauses between responses
  > **Warning**
  >
  > This is a **rough estimate** and may fail when multiple conversations
  > simultaneously request TTS generation. Your application must handle 429
  > errors gracefully when the actual concurrency limit is reached.

## Upgrading Limits

If your application requires higher concurrency limits, please contact our support team to discuss enterprise plans with increased limits.

> **Note**
>
> Concurrency limits are account basis. If you are using multiple models, all
> models share the same concurrency limit.

## Regions

Waves runs in two regions and automatically routes every request to the cluster nearest the client. No region selector is required - the routing is transparent to your application.

| Region | Location | Region-pinned hostname  |
| ------ | -------- | ----------------------- |
| India  | Mumbai   | `api.india.smallest.ai` |
| USA    | Oregon   | `api.us.smallest.ai`    |

Routing is based on network proximity and latency. Use a region-pinned hostname when you need traffic to stay in one region, for data residency or because you use [short-lived access tokens](/api-reference/token-based-authentication), which are valid only in the region that minted them. For anything beyond hostname pinning, contact [support@smallest.ai](mailto:support@smallest.ai).

> Understanding API concurrency limits and rate limiting.