# Gemini Token Usage

**URL:** <https://forum.langchain.com/t/gemini-token-usage/1697>\
**Category:** Observability & Evals\
**Tags:** python-help\
**Created:** [September 30, 2025, 8:07pm UTC](https://forum.langchain.com/t/gemini-token-usage/1697 "2025-09-30T20:07:39Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![imlevelhead](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/imlevelhead/32/1145_2.png) [@imlevelhead](https://forum.langchain.com/u/imlevelhead)\
**Post date:** [September 30, 2025, 8:07pm UTC](https://forum.langchain.com/t/gemini-token-usage/1697/1 "2025-09-30T20:07:39Z")

</div>

Howdy! I’m having trouble getting token usage to show up correctly in LangSmith when using Gemini models. Since there’s no Gemini wrapper, I can’t get the token metadata nested under `usage_metadata`, so it doesn’t roll up into the top-level LangGraph run summary. Here’s what OpenAI’s auto-formatted usage looks like vs. what I can produce with Gemini notice how mine isn’t under `usage_metadata`, so it’s not being summed.Could anyone share a pattern or example for shaping Gemini traces so token usage lands in `usage_metadata` and aggregates at the run level?

 ![Screenshot 2025-09-30 at 12.54.49 PM](https://canada1.discourse-cdn.com/flex007/uploads/langchain/original/2X/e/ebaca7dc374ab807c363a9ce29970a2e94bb879e.png)

---

<div class="post-metadata">

**Author:** ![imlevelhead](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/imlevelhead/32/1145_2.png) [@imlevelhead](https://forum.langchain.com/u/imlevelhead)\
**Post date:** [September 30, 2025, 8:08pm UTC](https://forum.langchain.com/t/gemini-token-usage/1697/2 "2025-09-30T20:08:22Z")

</div>

Here’s the openAI run

 ![Screenshot 2025-09-30 at 12.54.58 PM](https://canada1.discourse-cdn.com/flex007/uploads/langchain/original/2X/5/5bcf590696908ae69495b06bfad11dc0fc72cb33.png)