branch: elpa/gptel
commit d14d8c12f33829ea1615ac5316d7534d4175fe23
Author: Kien Nguyen <[email protected]>
Commit: Karthik Chikmagalur <[email protected]>
gptel-gh: Update with new models
gptel-gh.el (gptel--gh-models): Remove gpt-4o-copilot and o1, add
claude-haiku-4.
NEWS: Mention changes.
---
NEWS | 10 ++++++++--
gptel-gh.el | 22 ++++++++--------------
2 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/NEWS b/NEWS
index 63383bec4de..81b6f24ece3 100644
--- a/NEWS
+++ b/NEWS
@@ -4,6 +4,10 @@
** Breaking changes
+- The models =gpt-4-copilot= and =o1= have been removed from the default
+ list of GitHub Copilot models. These models are no longer available
+ in the GitHub Copilot API.
+
- Link handling in gptel chat buffers has changed, hopefully for the
better. When ~gptel-track-media~ is non-nil, gptel follows links in
the prompt and includes their contents with queries. Previously,
@@ -42,9 +46,11 @@
** New models and backends
-- GitHub Copilot backend: Add support for =gpt-5-codex= and
=claude-sonnet-4.5=.
+- GitHub Copilot backend: Add support for =gpt-5-codex=,
+ =claude-sonnet-4.5= and =claude-haiku-4.5=
-- Add support for =claude-sonnet-4-5-20250929= and =claude-haiku-4-5-20251001=.
+- Add support for =claude-sonnet-4-5-20250929= and
+ =claude-haiku-4-5-20251001=.
- Add support for =gemini-pro-latest=, =gemini-flash-latest= and
=gemini-flash-lite-latest=. These models point to the latest Gemini
diff --git a/gptel-gh.el b/gptel-gh.el
index 5f04da9de1d..392cd0ca45d 100644
--- a/gptel-gh.el
+++ b/gptel-gh.el
@@ -33,12 +33,6 @@
:capabilities (media tool-use json url)
:mime-types ("image/jpeg" "image/png" "image/gif" "image/webp")
:context-window 128 :input-cost 2.5 :output-cost 10 :cutoff-date
"2023-10")
- (gpt-4o-copilot
- :description "Cheap model for fast tasks; cheaper & more capable than
GPT-3.5 Turbo"
- :context-window 128
- :input-cost 0.15
- :output-cost 0.60
- :cutoff-date "2023-10")
(gpt-4.1
:description "Flagship model for complex tasks"
:capabilities (media tool-use json url)
@@ -71,14 +65,6 @@
:input-cost 0.25
:output-cost 2.0
:cutoff-date "2024-09")
- (o1
- :description "Reasoning model designed to solve hard problems across
domains"
- :capabilities (reasoning tool-use)
- :context-window 200
- :input-cost 15
- :output-cost 60
- :cutoff-date "2023-10"
- :request-params (:stream :json-false))
(o3
:description "Well-rounded and powerful model across domains"
:capabilities (reasoning media tool-use json url)
@@ -142,6 +128,14 @@
:input-cost 3
:output-cost 15
:cutoff-date "2025-07")
+ (claude-haiku-4.5
+ :description "Near-frontier intelligence at blazing speeds with extended
thinking"
+ :capabilities (media tool-use cache)
+ :mime-types ("image/jpeg" "image/png" "image/gif" "image/webp"
"application/pdf")
+ :context-window 144
+ :input-cost 1
+ :output-cost 5
+ :cutoff-date "2025-02")
(claude-opus-4
:description "Most capable model for complex reasoning and advanced
coding"
:capabilities (media tool-use cache)
