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

# Traffic

> Org-wide rate limits and cache settings applied across every gateway in your organization.

## What this is for

**Settings → Traffic** is where you set org-wide guardrails on the volume of requests and the caching behavior every gateway in your org enforces. Use it to cap traffic during a noisy launch, or to turn on response caching to absorb bursty workloads at lower latency and cost.

The page has two tabs: **Rate Limits** and **Cache**.

## Rate Limits

Card is titled **Global Rate Limits** with help text *"Org-wide limits applied across all gateways. Window is fixed at 1 minute."*

### Options

| Field                   | Notes                                                                                                                 |
| ----------------------- | --------------------------------------------------------------------------------------------------------------------- |
| **Enforcement**         | Master switch. When off, the limits below are not enforced.                                                           |
| **Requests per minute** | Maximum HTTP requests across all gateways in the org per 1-minute window. Set `0` to disable just this limit.         |
| **Tokens per minute**   | Maximum total prompt + completion tokens across all gateways per 1-minute window. Set `0` to disable just this limit. |

<Note>
  Per-key, per-user, per-team, and custom-window limits are not yet supported by the backend. Configure those at the API key level once available.
</Note>

### How to configure rate limits

<Frame caption="Traffic → Rate Limits">
  <img src="https://mintcdn.com/fcguardwayai/YAHzjsxByBObu8GF/images/screenshots/platform/settings/traffic-rate-limits.png?fit=max&auto=format&n=YAHzjsxByBObu8GF&q=85&s=478d4a2b407a26f54a404edb89c05224" alt="Global rate limits" width="2318" height="1158" data-path="images/screenshots/platform/settings/traffic-rate-limits.png" />
</Frame>

<Steps>
  <Step title="Open Settings → Traffic">
    Open **Settings → Traffic** from the dashboard sidebar. The **Rate Limits** tab is active by default.
  </Step>

  <Step title="Toggle enforcement">
    Turn **Enforcement** on. The numeric inputs below take effect on the next request.
  </Step>

  <Step title="Set the per-minute caps">
    Enter values for **Requests per minute** and **Tokens per minute** and click **Save**. Use `0` in either field to disable that specific limit while keeping the other one active.
  </Step>

  <Step title="Confirm enforcement">
    On a gateway, send traffic that crosses the threshold and confirm `request.rate_limited` events appear on [Logs](/platform/logs). Optionally subscribe to `request.rate_limited` on [Notifications](/platform/settings/notifications).
  </Step>
</Steps>

## Cache

Card is titled **Cache** with help text *"Org-wide cache configuration. Applies to every gateway in this org."*

### Options

| Field             | Notes                                                                                   |
| ----------------- | --------------------------------------------------------------------------------------- |
| **Enable cache**  | Master switch. When off, gateways serve every request from upstream.                    |
| **TTL (seconds)** | How long cache entries stay valid. `0` disables expiration.                             |
| **Max size (MB)** | Per-gateway upper bound on cache memory. Slider, range **256–8192 MB** in 256 MB steps. |

<Note>
  Strategy (exact / semantic / hybrid) and similarity-threshold tuning are not yet supported by the backend.
</Note>

### How to configure the cache

<Frame caption="Traffic → Cache">
  <img src="https://mintcdn.com/fcguardwayai/YAHzjsxByBObu8GF/images/screenshots/platform/settings/traffic-cache.png?fit=max&auto=format&n=YAHzjsxByBObu8GF&q=85&s=af0115d34ad2e9e26d71749cee727058" alt="Cache settings" width="2328" height="1170" data-path="images/screenshots/platform/settings/traffic-cache.png" />
</Frame>

<Steps>
  <Step title="Switch to the Cache tab">
    On **Settings → Traffic**, click the **Cache** tab.
  </Step>

  <Step title="Enable the cache">
    Turn **Enable cache** on.
  </Step>

  <Step title="Pick a TTL and max size">
    Set **TTL (seconds)** (start with `3600` for one hour) and slide **Max size (MB)** to a value the gateway host can spare. Click **Save**.
  </Step>

  <Step title="Verify hits">
    Replay a request that should hit the cache and confirm latency drops. Cached responses are flagged in [Logs](/platform/logs).
  </Step>
</Steps>

## Permissions

Owner and Admin can change rate limits and cache. Read Only users see the page but cannot save.

## Related

* [Logs](/platform/logs) — confirm rate-limit blocks and cache hits.
* [Notifications](/platform/settings/notifications) — fire on `request.rate_limited`.
* [API Keys](/platform/configuration/api-keys) — per-key request and token caps.