branch: elpa/gptel
commit 4034025d8a7dd781b923ea8fc45d1a60df761759
Author: Jack Kelly <[email protected]>
Commit: Karthik Chikmagalur <[email protected]>
gptel-openai-extras: Update grok model list
* gptel-openai-extras (gptel-make-xai):
- Add grok-4-1-fast and grok-4-fast (reasoning and non-reasoning)
- Reorder list to match https://docs.x.ai/developers/models
- Keep grok-4 since it is an alias to grok-4-0709
* NEWS: Mention additions.
---
NEWS | 9 +++++++--
gptel-openai-extras.el | 52 ++++++++++++++++++++++++++++++++------------------
2 files changed, 40 insertions(+), 21 deletions(-)
diff --git a/NEWS b/NEWS
index 76adb9c213..57f8622ec2 100644
--- a/NEWS
+++ b/NEWS
@@ -11,6 +11,11 @@
ChatGPT backend is created on the fly and used.
** New models and backends
+
+- xAI backend: Add support for =grok-4-1-fast-reasoning=,
+ =grok-4-1-fast-non-reasoning=, =grok-4-fast-reasoning=, and
+ =grok-4-fast-non-reasoning=.
+
** New features and UI changes
- When using ~setopt~ or the customize interface, ~gptel-backend~ can
@@ -459,7 +464,7 @@
~gptel-mcp-disconnect~. You can use these to start MCP servers
selectively and add tools to gptel. These commands are also
available from gptel's tools menu.
-
+
These commands are currently not autoloaded by gptel. To access
them, require the ~gptel-integrations~ feature.
@@ -501,7 +506,7 @@
path.
- The current kill can be added to gptel's context. To enable this,
- turn on ~gptel-expert-commands~ and use gptel's transient menu.
+ turn on ~gptel-expert-commands~ and use gptel's transient menu.
- The tools menu (~gptel-tools~) has been redesigned. It now displays
tool categories and associated tools in two columns, and it should
diff --git a/gptel-openai-extras.el b/gptel-openai-extras.el
index 493805cf16..f15d647a27 100644
--- a/gptel-openai-extras.el
+++ b/gptel-openai-extras.el
@@ -345,12 +345,19 @@ For the meanings of the keyword arguments, see
`gptel-make-openai'."
(protocol "https")
(endpoint "/v1/chat/completions")
(models
- '((grok-4
- :description "Grok Flagship model"
+ '((grok-4-1-fast-reasoning
+ :description "Fast tool-calling model"
:capabilities (tool-use json reasoning)
:context-window 256
- :input-cost 3
- :output-cost 15)
+ :input-cost 0.2
+ :output-cost 0.5)
+
+ (grok-4-1-fast-non-reasoning
+ :description "Fast tool-calling model (non-reasoning)"
+ :capabilities (tool-use json)
+ :context-window 256
+ :input-cost 0.2
+ :output-cost 0.5)
(grok-code-fast-1
:description "Fast reasoning model for agentic coding"
@@ -359,19 +366,26 @@ For the meanings of the keyword arguments, see
`gptel-make-openai'."
:input-cost 0.2
:output-cost 1.5)
- (grok-3
- :description "Grok 3"
+ (grok-4-fast-reasoning
+ :description "Fast tool-calling model"
:capabilities (tool-use json reasoning)
- :context-window 131
- :input-cost 3
- :output-cost 15)
+ :context-window 256
+ :input-cost 0.2
+ :output-cost 0.5)
+
+ (grok-4-fast-non-reasoning
+ :description "Fast tool-calling model (non-reasoning)"
+ :capabilities (tool-use json)
+ :context-window 256
+ :input-cost 0.2
+ :output-cost 0.5)
- (grok-3-fast
- :description "Faster Grok 3"
+ (grok-4
+ :description "Grok Flagship model"
:capabilities (tool-use json reasoning)
- :context-window 131
- :input-cost 5
- :output-cost 25)
+ :context-window 256
+ :input-cost 3
+ :output-cost 15)
(grok-3-mini
:description "Mini Grok 3"
@@ -380,12 +394,12 @@ For the meanings of the keyword arguments, see
`gptel-make-openai'."
:input-cost 0.3
:output-cost 0.5)
- (grok-3-mini-fast
- :description "Faster mini Grok 3"
+ (grok-3
+ :description "Grok 3"
:capabilities (tool-use json reasoning)
- :context-window 131072
- :input-cost 0.6
- :output-cost 4)
+ :context-window 131
+ :input-cost 3
+ :output-cost 15)
(grok-2-vision-1212
:description "Grok 2 Vision"
