grp-overage-alerting: Add consumption usage based alert notifications

content/en/docs/genai/mendix-cloud-genai/navigate-mxgenai.md

@@ -37,6 +37,17 @@ Below the summary, the page shows **Consumption Over Selected Time Range**. You
 * **Monthly Bundle Output Consumption** – Raw LLM output tokens consumed per day.
 * **Monthly Bundle API Calls** – Number of API calls made under the resource per day within a bundle month.
 
+### Consumption Limit Notifications {#consumption-limit-notifications}
+
+Mendix notifies you when a resource approaches or reaches its monthly GenAI Unit allocation:
+
+* **80% of the allocation** – The resource's [Technical Contact](#technical-contact) receives an email that the resource is approaching its limit. A yellow **Consumption limit warning** banner and a **REACHING TOKEN LIMIT** label appear on the resource in the resource overview and on the resource details page.
+* **100% of the allocation** – The Technical Contact receives an email that the resource has reached its limit. A red **Token limit reached** banner and a **TOKEN LIMIT EXCEEDED** label appear on the resource in the resource overview and on the resource details page.
+
+{{< figure src="/attachments/genai/navigate_mxgenai/token-limit-exceeded.png" alt="Resource details page with a red Token limit reached banner at the top and a TOKEN LIMIT EXCEEDED label on the GenAI Units card, showing 355 of 300 GenAI Units consumed (118%)" >}}
+
+To increase the allocation, see [Adjusting the GenAI Unit Capacity of a Resource](#adjusting-the-genai-unit-capacity-of-a-resource).
+
 ### What Are Tokens and GenAI Units?
 
 LLM tokens (not to be confused with [Mendix Cloud Tokens](/control-center/cloud-tokens/)) are what you pay for when consuming large language model services. Text input is first "tokenized," meaning it is broken down into smaller pieces where each piece represents a token. A good rule of thumb is that 100 tokens are around 75 English words, though this varies by model and language. Tokens sent to the model are called input tokens; tokens generated by the model are called output tokens.
@@ -67,7 +78,7 @@ Each resource has one Technical Contact. The Technical Contact is the person who
 
 * Upcoming model deprecations and new models
 * Planned maintenance
-* Overage alerts, including token limit notifications
+* Overage alerts, including [consumption limit notifications](#consumption-limit-notifications)
 * Other notifications related to the resource
 
 The Technical Contact is responsible for informing the development teams or managers on how to proceed. In the **Overview** tab, the Technical Contact is marked with a **TECHNICAL CONTACT** label next to their name.