langgenius/dify-official-plugins
1
0
Fork 0
mirror of https://github.com/langgenius/dify-official-plugins.git synced 2026-07-21 17:45:23 -04:00
Code Issues 54 Packages Projects Releases Wiki Activity

[PR #2048] [MERGED] feat(xai): add grok-4-fast-reasoning and grok-4-fast-non-reasoning models #2225

New Issue
Closed
opened 2026-02-16 11:16:24 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 11:16:24 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langgenius/dify-official-plugins/pull/2048
Author: @leozanee
Created: 11/12/2025
Status: ✅ Merged
Merged: 11/12/2025
Merged by: @crazywoola

Base: main ← Head: feat-add-plugin-model-rjVoC

📝 Commits (1)

  • 6cab7af feat(xai): add grok-4-fast-reasoning and grok-4-fast-non-reasoning models

📊 Changes

3 files changed (+111 additions, -1 deletions)

View changed files

📝 models/x/manifest.yaml (+1 -1)
➕ models/x/models/llm/grok-4-fast-non-reasoning.yaml (+50 -0)
➕ models/x/models/llm/grok-4-fast-reasoning.yaml (+60 -0)

📄 Description

Add grok-4-fast-reasoning and grok-4-fast-non-reasoning models

Changes

  • Added grok-4-fast-reasoning model with reasoning capabilities
  • Added grok-4-fast-non-reasoning model (faster variant)
  • Updated manifest version to 0.0.14

Model Specifications

  • Context window: 2,000,000 tokens
  • Pricing: $0.20 input / $0.50 output per million tokens
  • Features: Vision, tool calling, live search, structured outputs

Testing Results

Tested with logic problems to verify reasoning functionality:

  • Reasoning version: 5.25s response time, 1277 tokens output
  • Non-reasoning version: 3.91s response time, 1033 tokens output
  • Performance difference: 34% longer processing time and 24% more detailed output confirms reasoning functionality is working

Model Configuration

Both models include:

  • ✅ Vision input support
  • ✅ Tool calling (multi-tool-call, stream-tool-call)
  • ✅ Live search parameters
  • ✅ Structured outputs (json_object, json_schema)
  • ✅ use_encrypted_content parameter for accessing encrypted reasoning content (reasoning model only)

References

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langgenius/dify-official-plugins/pull/2048 **Author:** [@leozanee](https://github.com/leozanee) **Created:** 11/12/2025 **Status:** ✅ Merged **Merged:** 11/12/2025 **Merged by:** [@crazywoola](https://github.com/crazywoola) **Base:** `main` ← **Head:** `feat-add-plugin-model-rjVoC` --- ### 📝 Commits (1) - [`6cab7af`](https://github.com/langgenius/dify-official-plugins/commit/6cab7af8a821ba87a12f0e1eb89c37a2add93a80) feat(xai): add grok-4-fast-reasoning and grok-4-fast-non-reasoning models ### 📊 Changes **3 files changed** (+111 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `models/x/manifest.yaml` (+1 -1) ➕ `models/x/models/llm/grok-4-fast-non-reasoning.yaml` (+50 -0) ➕ `models/x/models/llm/grok-4-fast-reasoning.yaml` (+60 -0) </details> ### 📄 Description ## Add grok-4-fast-reasoning and grok-4-fast-non-reasoning models ### Changes - Added `grok-4-fast-reasoning` model with reasoning capabilities - Added `grok-4-fast-non-reasoning` model (faster variant) - Updated manifest version to 0.0.14 ### Model Specifications - **Context window**: 2,000,000 tokens - **Pricing**: $0.20 input / $0.50 output per million tokens - **Features**: Vision, tool calling, live search, structured outputs ### Testing Results Tested with logic problems to verify reasoning functionality: - **Reasoning version**: 5.25s response time, 1277 tokens output - **Non-reasoning version**: 3.91s response time, 1033 tokens output - **Performance difference**: 34% longer processing time and 24% more detailed output confirms reasoning functionality is working ### Model Configuration Both models include: - ✅ Vision input support - ✅ Tool calling (multi-tool-call, stream-tool-call) - ✅ Live search parameters - ✅ Structured outputs (json_object, json_schema) - ✅ `use_encrypted_content` parameter for accessing encrypted reasoning content (reasoning model only) ### References - xAI Models Documentation: https://docs.x.ai/docs/models - xAI Reasoning Guide: https://docs.x.ai/docs/guides/reasoning --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-16 11:16:24 -05:00
yindo closed this issue 2026-02-16 11:16:24 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
bug
bug
dependencies
documentation
enhancement
good first issue
invalid
pull-request
Mirrored from GitHub Pull Request
 question
stale
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify-official-plugins#2225
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?