Release Notes: - N/A
Showing the changes to docs/src (1 of 1 file). Show all
Unified · Split
| @@ -226,7 +226,9 @@ Zed will also use the `GOOGLE_AI_API_KEY` environment variable if it's defined. · 225 unmodified lines | ||
| 226 | 226 | |
| 227 | 227 | #### Custom Models {#google-ai-custom-models} |
| 228 | 228 | |
| 229 | −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`: | |
| 229 | +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. | |
| 230 | + | |
| 231 | +Here is an example of a custom Google AI model you could add to your Zed `settings.json`: | |
| 230 | 232 | |
| 231 | 233 | ```json |
| 232 | 234 | { |
| @@ -234,9 +236,13 @@ By default, Zed will use `stable` versions of models, but you can use specific v · 1 unmodified line | ||
| 234 | 236 | "google": { |
| 235 | 237 | "available_models": [ |
| 236 | 238 | { |
| 237 | − "name": "gemini-1.5-flash-latest", | |
| 238 | − "display_name": "Gemini 1.5 Flash (Latest)", | |
| 239 | − "max_tokens": 1000000 | |
| 239 | + "name": "gemini-2.5-flash-preview-05-20", | |
| 240 | + "display_name": "Gemini 2.5 Flash (Thinking)", | |
| 241 | + "max_tokens": 1000000, | |
| 242 | + "mode": { | |
| 243 | + "type": "thinking", | |
| 244 | + "budget_tokens": 24000 | |
| 245 | + } | |
| 240 | 246 | } |
| 241 | 247 | ] |
| 242 | 248 | } |