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

# Configure account settings

> Configure account-wide AI Gateway timeouts and token limits.

Account-wide gateway settings apply to every request through `https://gateway.ngrok.ai`, so you can set defaults like timeouts and token limits once instead of repeating them on every [access key configuration](/ai-gateway/guides/access-key-configurations).

## Timeouts

| Setting             | Default | Description                                            |
| ------------------- | ------- | ------------------------------------------------------ |
| `perRequestTimeout` | `60s`   | Max time for a single upstream attempt                 |
| `totalTimeout`      | `120s`  | Max time for a request including all failover attempts |

If a single attempt exceeds `perRequestTimeout`, the gateway moves to the next failover candidate. If total time exceeds `totalTimeout`, the gateway returns an error.

## Token limits

| Setting           | Default | Description                                  |
| ----------------- | ------- | -------------------------------------------- |
| `maxInputTokens`  | none    | Reject requests above estimated input tokens |
| `maxOutputTokens` | none    | Cap completion length                        |

Leave token limits unset for no cap. Set them to block oversized requests before they reach upstream providers.

## Via dashboard

1. Open [Settings](https://app.ngrok.ai/settings) in app.ngrok.ai
2. Edit **Total timeout**, **Per-request timeout**, and optional token limits
3. Save

The **Settings** page also shows the gateway URL (`https://gateway.ngrok.ai`) and lets you manage [AI Gateway API keys](/ai-gateway/concepts/access-keys#credentials-overview) for automation.

## Via the AI Gateway API

Get current settings:

```bash theme={null}
curl https://api.ngrok.ai/gateway-config \
  -H "Authorization: Bearer $AI_GATEWAY_API_KEY"
```

Update settings (omitted fields keep their current values):

```bash theme={null}
curl -X PATCH https://api.ngrok.ai/gateway-config \
  -H "Authorization: Bearer $AI_GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "totalTimeout": "120s",
    "perRequestTimeout": "60s",
    "maxInputTokens": 128000,
    "maxOutputTokens": 8192
  }'
```

Clear a token limit by sending `null`:

```bash theme={null}
curl -X PATCH https://api.ngrok.ai/gateway-config \
  -H "Authorization: Bearer $AI_GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "maxInputTokens": null }'
```

Duration fields use Go duration strings (for example, `30s`, `2m`).

See the [Gateway configuration API reference](/ai-gateway/api-reference/gateway-config/get).

## Next steps

* [How It Works](/ai-gateway/how-it-works): Request flow and failover
* [Choose how to reach providers](/ai-gateway/guides/configuring-providers): Credits, provider keys, and self-run models
* [Access Key Configurations](/ai-gateway/guides/access-key-configurations): Per-key scope and routing