From 08ad50763731f2d322f0001db17f435f8d80c1d2 Mon Sep 17 00:00:00 2001 From: Cohee <18619528+Cohee1207@users.noreply.github.com> Date: Sun, 25 May 2025 13:43:16 +0300 Subject: [PATCH] Split reasoning effort tooltips from claude/google. --- public/index.html | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/public/index.html b/public/index.html index 106c53d33..a7c62b44f 100644 --- a/public/index.html +++ b/public/index.html @@ -2081,8 +2081,11 @@
OpenAI-style options: low, medium, high. Minimum and maximum are aliased to low and high. Auto does not send an effort level.
-
- Allocates a portion of the response length for thinking (low: 10%, medium: 25%, high: 50%). Other options are model-dependent. +
+ Allocates a portion of the response length for thinking (min: 1024 tokens, low: 10%, medium: 25%, high: 50%, max: 95%), but minimum 1024 tokens. Auto does not request thinking. +
+
+ Allocates a portion of the response length for thinking (min: 0 tokens, low: 10%, medium: 25%, high: 50%, max: 24576 tokens). Auto lets the model decide.