# rate_limits

> Peak-minute utilisation of requests, input tokens and output tokens per minute by deployment and model, against the provider quota and the gateway's pacing limit, with throttles and pacing waits.

Peak-minute utilisation of requests, input tokens and output tokens per minute by deployment and model, against the provider quota and the gateway’s pacing limit, with throttles and pacing waits. range: 1h, 24h or 7d.

**Role:** viewer and above (any person, AAL staff, machine key).

**Acts:** no. It only reads; nothing an AI agent calls through MCP approves, pays, or changes a limit.

## Inputs

| Input        | Type           | Default |
| ------------ | -------------- | ------- |
| `range`      | string         | `"24h"` |
| `deployment` | string or null | `null`  |
| `provider`   | string or null | `null`  |
| `model`      | string or null | `null`  |

## Call

The arguments of a `tools/call` request:

```json
{
  "name": "rate_limits",
  "arguments": {}
}
```

Source: https://docs.atlanticagenticlabs.com/mcp/tools/rate-limits/