# Access to the tokenUsageEstimate object at the output of a Chat Model node

**URL:** <https://community.n8n.io/t/access-to-the-tokenusageestimate-object-at-the-output-of-a-chat-model-node/141691>\
**Category:** Questions\
**Tags:** node\
**Created:** [1. Juli 2025 um 14:15 UTC](https://community.n8n.io/t/access-to-the-tokenusageestimate-object-at-the-output-of-a-chat-model-node/141691 "2025-07-01T14:15:14Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![hubschrauber](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/hubschrauber/32/46788_2.png) [@hubschrauber](https://community.n8n.io/u/hubschrauber)\
**Post date:** [1. Juli 2025 um 14:44 UTC](https://community.n8n.io/t/access-to-the-tokenusageestimate-object-at-the-output-of-a-chat-model-node/141691/2 "2025-07-01T14:44:25Z")

</div>

You probably aren’t doing anything wrong. The bits of data (token usage stats) that you want to access probably just aren’t passed along or exposed in any way you can use in a workflow. There’s a discussion about this already [here](http://community.n8n.io/t/how-to-get-ai-token-usage-information-from-ai-agent/94671) where various things were tried, but I don’t think anything ever worked.

There is a relatively highly voted [feature request](http://community.n8n.io/t/retrieve-llm-token-usage-in-ai-agents/68714) about this, if you want to add your vote to it.

---

_[View the full topic](https://community.n8n.io/t/access-to-the-tokenusageestimate-object-at-the-output-of-a-chat-model-node/141691)._