branch: externals/llm
commit 14af3e3aae33e8c9320f296bcadfa7ee22517e78
Author: Andrew Hyatt <ahy...@gmail.com>
Commit: GitHub <nore...@github.com>
Add Gemini 2.5 Pro model support (#179)
---
NEWS.org | 1 +
llm-models.el | 5 +++++
2 files changed, 6 insertions(+)
diff --git a/NEWS.org b/NEWS.org
index 33c0cbda90..5412ce31f7 100644
--- a/NEWS.org
+++ b/NEWS.org
@@ -1,6 +1,7 @@
* Version 0.24.2
- Fix issue with some Open AI compatible providers needing models to be passed
by giving a non-nil default.
* Version 0.24.1
+- Add Gemini 2.5 Pro
- Fix issue with Ollama incorrect requests when passing non-standard params.
- Fix issue with JSON return specs which pass booleans
* Version 0.24.0
diff --git a/llm-models.el b/llm-models.el
index 8015dbac54..dbedeced80 100644
--- a/llm-models.el
+++ b/llm-models.el
@@ -142,6 +142,11 @@ REGEX is a regular expression that can be used to identify
the model, uniquely (
:capabilities '(generation)
:context-length 32768
:regex "gemini-2\\.0-flash-thinking")
+ (make-llm-model
+ :name "Gemini 2.5 Pro" :symbol 'gemini-2.5-pro
+ :capabilities '(generation tool-use image-input audio-input video-input)
+ :context-length 1048576
+ :regex "gemini-2\\.5-pro")
(make-llm-model
:name "Gemini 2.0 Pro" :symbol 'gemini-2.0-pro
:capabilities '(generation tool-use image-input audio-input video-input)
