Replies: 1 comment
-
They've responded to this many times. They don't want to do it in general because they have a vision of multi-model routing. Most of that involves Flash doing more things (like search, summarization, and compaction, loop detection), but they want to decide for you. Originally, it asked Flash each time where the request should be routed, but they removed it. If you truly want this, you can come downstream: https://github.com/acoliver/llxprt-code - it is a fork but we stay up with gemini-cli's latest features and releases, but support more models, and you can choose your model with /model or --model among other things. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Not all tasks require Pro, some lightweight tasks are much more suited for Flash
Beta Was this translation helpful? Give feedback.
All reactions