Yehowshua/ZIm
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: Gemini thinking budget configuration (#32002)

Browse source 
Release Notes:

- N/A
This commit is contained in:
Oleksiy Syvokon 2025-06-03 20:41:42 +03:00 • committed by GitHub
parent 29cb95a3ca
commit 1bc052d76b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 10 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

14
docs/src/ai/configuration.md
View file

@ -226,7 +226,9 @@ Zed will also use the `GOOGLE_AI_API_KEY` environment variable if it's defined.
#### Custom Models {#google-ai-custom-models}
By default, Zed will use `stable` versions of models, but you can use specific versions of models, including [experimental models](https://ai.google.dev/gemini-api/docs/models/experimental-models), with the Google AI provider by adding the following to your Zed `settings.json`:
By default, Zed will use `stable` versions of models, but you can use specific versions of models, including [experimental models](https://ai.google.dev/gemini-api/docs/models/experimental-models). You can configure a model to use [thinking mode](https://ai.google.dev/gemini-api/docs/thinking) (if it supports it) by adding a `mode` configuration to your model. This is useful for controlling reasoning token usage and response speed. If not specified, Gemini will automatically choose the thinking budget.
Here is an example of a custom Google AI model you could add to your Zed `settings.json`:
```json
{
@ -234,9 +236,13 @@ By default, Zed will use `stable` versions of models, but you can use specific v
"google": {
"available_models": [
{
"name": "gemini-1.5-flash-latest",
"display_name": "Gemini 1.5 Flash (Latest)",
"max_tokens": 1000000
"name": "gemini-2.5-flash-preview-05-20",
"display_name": "Gemini 2.5 Flash (Thinking)",
"max_tokens": 1000000,
"mode": {
"type": "thinking",
"budget_tokens": 24000
}
}
]
}