# language_models: Count Google AI tokens through LLM service \(\#29319\) · gitcafe/zed

[View on GitCafe](https://git.cafe/gitcafe/zed/commit/fef2681cfaa9fcaa72436a2ca9da79f84f5bee4c)

Repository: [gitcafe/zed](https://git.cafe/gitcafe/zed)

Visibility: public

Requested revision: fef2681cfaa9fcaa72436a2ca9da79f84f5bee4c

Requested commit: fef2681cfaa9fcaa72436a2ca9da79f84f5bee4c

Commit: fef2681cfaa9fcaa72436a2ca9da79f84f5bee4c

Tree: e41a40796ff640e473b320040a1c67eec9be0a82

Author: Marshall Bowers

Committer: GitHub

## Message

```
language_models: Count Google AI tokens through LLM service (#29319)

This PR wires the counting of Google AI tokens back up.

It now goes through the LLM service instead of collab's RPC.

Still only available for Zed staff.

Release Notes:

- N/A
```

## Parents

- [8b5835de171349d0d0e5aaa5f1563934b98e98c0](https://git.cafe/gitcafe/zed/commit/8b5835de171349d0d0e5aaa5f1563934b98e98c0?format=markdown)

[Source at this commit](https://git.cafe/gitcafe/zed/tree/fef2681cfaa9fcaa72436a2ca9da79f84f5bee4c?format=markdown)