Grok4 fast models #94
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Add grok auth login command for API key setup - Open xAI console for login and key creation - Support manual key entry with validation - Add management key support for auto-generating API keys - Include verbose guidance for free/paid plan setup - Team limits unlocked with paid plan API keys
- Integrate Puppeteer for browser automation - Auto-launch browser, wait for user login, generate API key - Extend settings for future OAuth tokens (access/refresh) - Add auto-trigger on first run when no API key found - Fallback to manual entry if automation fails - Prepare for xAI OAuth when available
- Remove Puppeteer placeholders for reliable manual flow - Keep management key auto-gen for paid plans - Comprehensive user guidance and validation - Auto-trigger on first run - Fallback from API to manual entry - Ready for xAI management API when available
…on-reasoning) to default models list
Author
Add Grok 4 Fast ModelsThis PR adds the new Grok 4 Fast model variants to the default models list: New Models Added:
Changes:
Usage:grok --model grok-4-fast-reasoning "Complex reasoning task"
grok --model grok-4-fast-non-reasoning "Quick response needed" |
|
Is there a plan to get this merged? |
Author
I am not the maintainer so I don't know, also the reasoning model [EDIT] works pretty well now, despite having issues before, it took a grok CLI reboot to work so everyone may need to reboot. To be tested |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
(adding grok 4 fast models, more details below)
Checklist
___ SECURITY AND TYPECHECK TESTED AND PASSED, MODELS PASSED WHEN TESTED_____
Add Grok 4 Fast Models
This PR adds the new Grok 4 Fast model variants to the default models list:
New Models Added:
grok-4-fast-reasoning- For tasks needing deeper reasoning and chain-of-thoughtgrok-4-fast-non-reasoning- For quicker, non-reasoning responsesChanges:
Usage: