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 #1492] [MERGED] add claude & deepseek & google & gpt models #1922

New Issue
Closed
opened 2026-02-16 11:15:14 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 11:15:14 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langgenius/dify-official-plugins/pull/1492
Author: @guangtouwangba
Created: 8/12/2025
Status: ✅ Merged
Merged: 8/12/2025
Merged by: @crazywoola

Base: main ← Head: feat/update-openrouter

📝 Commits (4)

📊 Changes

24 files changed (+1280 additions, -6 deletions)

View changed files

📝 models/openrouter/manifest.yaml (+1 -1)
📝 models/openrouter/models/llm/_position.yaml (+20 -0)
➕ models/openrouter/models/llm/claude-opus-4.1.yaml (+62 -0)
➕ models/openrouter/models/llm/claude-opus-4.yaml (+55 -0)
➕ models/openrouter/models/llm/deepseek-chat-v3-0324.yaml (+61 -0)
📝 models/openrouter/models/llm/deepseek-chat.yaml (+6 -4)
➕ models/openrouter/models/llm/deepseek-prover-v2.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-r1-0528-qwen3-8b.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-r1-0528.yaml (+63 -0)
➕ models/openrouter/models/llm/deepseek-r1-distill-llama-70b.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-r1-distill-llama-8b.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-r1-distill-qwen-1.5b.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-r1-distill-qwen-14b.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-r1-distill-qwen-32b.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-r1-distill-qwen-7b.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-r1.yaml (+61 -0)
➕ models/openrouter/models/llm/deepseek-v3-base.yaml (+59 -0)
📝 models/openrouter/models/llm/gemini-1.5-flash.yaml (+1 -1)
➕ models/openrouter/models/llm/gemini-2.5-flash-lite.yaml (+89 -0)
➕ models/openrouter/models/llm/gemma-3n-e2b-it-free.yaml (+52 -0)

...and 4 more files

📄 Description

Related Issues or Context

Adding multiple new DeepSeek and Claude Opus 4 models to OpenRouter provider to support the latest AI models available on OpenRouter platform.

Context:

  • DeepSeek has released multiple new R1 series reasoning models and distilled variants
  • Anthropic released Claude Opus 4, benchmarked as world's best coding model
  • OpenRouter now supports these models but they were missing from Dify's OpenRouter plugin
  • Updated existing DeepSeek V3 model configuration to match current OpenRouter specifications

This PR contains Changes to Non-Plugin

  • Documentation
  • Other

This PR contains Changes to Non-LLM Models Plugin

  • I have Run Comprehensive Tests Relevant to My Changes

This PR contains Changes to LLM Models Plugin

  • My Changes Affect Message Flow Handling (System Messages and User→Assistant Turn-Taking)

  • My Changes Affect Tool Interaction Flow (Multi-Round Usage and Output Handling, for both Agent App and Agent Node)

  • My Changes Affect Multimodal Input Handling (Images, PDFs, Audio, Video, etc.)

  • My Changes Affect Multimodal Output Generation (Images, Audio, Video, etc.)

  • My Changes Affect Structured Output Format (JSON, XML, etc.)

  • My Changes Affect Token Consumption Metrics

  • My Changes Affect Other LLM Functionalities (Reasoning Process, Grounding, Prompt Caching, etc.)

  • Other Changes (Add New Models, Fix Model Parameters etc.)

Models Added/Updated:

New DeepSeek Models:

  1. deepseek-r1 - Original R1 reasoning model (671B params, $0.40/$2.00)
  2. deepseek-r1-distill-qwen-32b - 32B distilled model ($0.075/$0.15)
  3. deepseek-r1-distill-qwen-14b - 14B distilled model ($0.15/$0.15)
  4. deepseek-r1-distill-llama-70b - 70B Llama-based distilled model ($0.033/$0.133)
  5. deepseek-r1-distill-llama-8b - 8B Llama-based distilled model ($0.04/$0.04)
  6. deepseek-r1-distill-qwen-1.5b - 1.5B ultra-efficient model ($0.18/$0.18)
image image

New Anthropic Model:

  1. claude-opus-4 - World's best coding model (200K context, $15/$75)
  2. claude-opus-4.1
image

New Google Model:

  1. gemini-2.5-flash-lite - Lightweight reasoning model (1M context, $0.10/$0.40)
  2. gemma-3n-e2b-it:free - Free multimodal model (8K context, $0/$0)
    image
    image

OpenAI GPT-5 Series (4 models):

  1. gpt-5 - Most advanced model (400K context, $1.25/$10.00, requires BYOK)
  2. gpt-5-chat - Enterprise conversation model (400K context, $1.25/$10.00)
  3. gpt-5-mini - Compact reasoning model (400K context, $0.25/$2.00)
  4. gpt-5-nano - Ultra-fast variant (400K context, $0.05/$0.40)
    image

Updated Existing Model:

  • deepseek-chat - Updated to reflect DeepSeek V3 specifications (163K context, $0.18/$0.72, added tool calling features)

Features Added:

  • All new models support reasoning capabilities (agent-thought)
  • DeepSeek R1 models support reasoning token hiding (exclude_reasoning_tokens)
  • Claude Opus 4 supports vision, document processing, and advanced tool calling
  • Updated context sizes and pricing to match current OpenRouter specifications

Version Control (Any Changes to the Plugin Will Require Bumping the Version)

  • I have Bumped Up the Version in Manifest.yaml (Top-Level Version Field, Not in Meta Section)

Version changed from 0.0.15 to 0.0.16 (incremented through multiple model additions)

Dify Plugin SDK Version

  • I have Ensured dify_plugin>=0.3.0,<0.5.0 is in requirements.txt

Environment Verification (If Any Code Changes)

Local Deployment Environment

  • Dify Version is: , I have Tested My Changes on Local Deployment Dify with a Clean Environment That Matches the Production Configuration.

SaaS Environment

  • I have Tested My Changes on cloud.dify.ai with a Clean Environment That Matches the Production Configuration

Summary: This PR adds 7 new cutting-edge AI models to the OpenRouter provider and updates 1 existing model configuration, ensuring Dify users have access to the latest DeepSeek R1 reasoning models and Claude Opus 4 coding capabilities. All models are configured with appropriate pricing, context sizes, and feature flags according to OpenRouter's current specifications.

🔄 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/1492 **Author:** [@guangtouwangba](https://github.com/guangtouwangba) **Created:** 8/12/2025 **Status:** ✅ Merged **Merged:** 8/12/2025 **Merged by:** [@crazywoola](https://github.com/crazywoola) **Base:** `main` ← **Head:** `feat/update-openrouter` --- ### 📝 Commits (4) - [`23154f9`](https://github.com/langgenius/dify-official-plugins/commit/23154f9fb94a429e3b24d5c83e574c2f605214bd) add claude & deepseek models - [`6832dd1`](https://github.com/langgenius/dify-official-plugins/commit/6832dd1051d25a8d8e9defd5320b578a05fe3787) add google models - [`687d2b6`](https://github.com/langgenius/dify-official-plugins/commit/687d2b618f8fee3100bb0adb7fd6a1146b22f0d7) add openai models - [`0830aa1`](https://github.com/langgenius/dify-official-plugins/commit/0830aa11fa124fb77407e9c1cac263e10738f3c5) update openrouter version ### 📊 Changes **24 files changed** (+1280 additions, -6 deletions) <details> <summary>View changed files</summary> 📝 `models/openrouter/manifest.yaml` (+1 -1) 📝 `models/openrouter/models/llm/_position.yaml` (+20 -0) ➕ `models/openrouter/models/llm/claude-opus-4.1.yaml` (+62 -0) ➕ `models/openrouter/models/llm/claude-opus-4.yaml` (+55 -0) ➕ `models/openrouter/models/llm/deepseek-chat-v3-0324.yaml` (+61 -0) 📝 `models/openrouter/models/llm/deepseek-chat.yaml` (+6 -4) ➕ `models/openrouter/models/llm/deepseek-prover-v2.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-r1-0528-qwen3-8b.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-r1-0528.yaml` (+63 -0) ➕ `models/openrouter/models/llm/deepseek-r1-distill-llama-70b.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-r1-distill-llama-8b.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-r1-distill-qwen-1.5b.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-r1-distill-qwen-14b.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-r1-distill-qwen-32b.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-r1-distill-qwen-7b.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-r1.yaml` (+61 -0) ➕ `models/openrouter/models/llm/deepseek-v3-base.yaml` (+59 -0) 📝 `models/openrouter/models/llm/gemini-1.5-flash.yaml` (+1 -1) ➕ `models/openrouter/models/llm/gemini-2.5-flash-lite.yaml` (+89 -0) ➕ `models/openrouter/models/llm/gemma-3n-e2b-it-free.yaml` (+52 -0) _...and 4 more files_ </details> ### 📄 Description ## Related Issues or Context Adding multiple new DeepSeek and Claude Opus 4 models to OpenRouter provider to support the latest AI models available on OpenRouter platform. ### Context: - DeepSeek has released multiple new R1 series reasoning models and distilled variants - Anthropic released Claude Opus 4, benchmarked as world's best coding model - OpenRouter now supports these models but they were missing from Dify's OpenRouter plugin - Updated existing DeepSeek V3 model configuration to match current OpenRouter specifications ## This PR contains Changes to *Non-Plugin* - [ ] Documentation - [ ] Other ## This PR contains Changes to *Non-LLM Models Plugin* - [ ] I have Run Comprehensive Tests Relevant to My Changes ## This PR contains Changes to *LLM Models Plugin* - [ ] My Changes Affect Message Flow Handling (System Messages and User→Assistant Turn-Taking) - [ ] My Changes Affect Tool Interaction Flow (Multi-Round Usage and Output Handling, for both Agent App and Agent Node) - [ ] My Changes Affect Multimodal Input Handling (Images, PDFs, Audio, Video, etc.) - [ ] My Changes Affect Multimodal Output Generation (Images, Audio, Video, etc.) - [ ] My Changes Affect Structured Output Format (JSON, XML, etc.) - [ ] My Changes Affect Token Consumption Metrics - [ ] My Changes Affect Other LLM Functionalities (Reasoning Process, Grounding, Prompt Caching, etc.) - [x] Other Changes (Add New Models, Fix Model Parameters etc.) ### Models Added/Updated: #### New DeepSeek Models: 1. **deepseek-r1** - Original R1 reasoning model (671B params, $0.40/$2.00) 2. **deepseek-r1-distill-qwen-32b** - 32B distilled model ($0.075/$0.15) 3. **deepseek-r1-distill-qwen-14b** - 14B distilled model ($0.15/$0.15) 4. **deepseek-r1-distill-llama-70b** - 70B Llama-based distilled model ($0.033/$0.133) 5. **deepseek-r1-distill-llama-8b** - 8B Llama-based distilled model ($0.04/$0.04) 6. **deepseek-r1-distill-qwen-1.5b** - 1.5B ultra-efficient model ($0.18/$0.18) <img width="830" height="331" alt="image" src="https://github.com/user-attachments/assets/76cdea29-a63b-48ed-96a4-52974a90843a" /> <img width="334" height="354" alt="image" src="https://github.com/user-attachments/assets/5f4a0ec4-8610-4f86-b447-485604607843" /> #### New Anthropic Model: 8. **claude-opus-4** - World's best coding model (200K context, $15/$75) 9. **claude-opus-4.1** <img width="782" height="310" alt="image" src="https://github.com/user-attachments/assets/570853af-4b2c-424c-908c-99ac8c82c0f0" /> #### New Google Model: 10. gemini-2.5-flash-lite - Lightweight reasoning model (1M context, $0.10/$0.40) 11. gemma-3n-e2b-it:free - Free multimodal model (8K context, $0/$0) <img width="843" height="289" alt="image" src="https://github.com/user-attachments/assets/caf80b8d-7e01-4ea0-8770-b0c88aa7c680" /> <img width="304" height="225" alt="image" src="https://github.com/user-attachments/assets/f9068b50-30c2-4f21-9e15-5f8c6f297af6" /> #### OpenAI GPT-5 Series (4 models): 13. gpt-5 - Most advanced model (400K context, $1.25/$10.00, requires BYOK) 14. gpt-5-chat - Enterprise conversation model (400K context, $1.25/$10.00) 15. gpt-5-mini - Compact reasoning model (400K context, $0.25/$2.00) 16. gpt-5-nano - Ultra-fast variant (400K context, $0.05/$0.40) <img width="323" height="198" alt="image" src="https://github.com/user-attachments/assets/11b814aa-cdef-42c6-8c22-f75fdcfdbc7c" /> #### Updated Existing Model: - **deepseek-chat** - Updated to reflect DeepSeek V3 specifications (163K context, $0.18/$0.72, added tool calling features) ### Features Added: - All new models support reasoning capabilities (`agent-thought`) - DeepSeek R1 models support reasoning token hiding (`exclude_reasoning_tokens`) - Claude Opus 4 supports vision, document processing, and advanced tool calling - Updated context sizes and pricing to match current OpenRouter specifications ## Version Control (Any Changes to the Plugin Will Require Bumping the Version) - [x] I have Bumped Up the Version in Manifest.yaml (Top-Level `Version` Field, Not in Meta Section) **Version changed from 0.0.15 to 0.0.16** (incremented through multiple model additions) ## Dify Plugin SDK Version - [x] I have Ensured `dify_plugin>=0.3.0,<0.5.0` is in requirements.txt ## Environment Verification (If Any Code Changes) ### Local Deployment Environment - [ ] Dify Version is: <!-- 1.4.0+ -->, I have Tested My Changes on Local Deployment Dify with a Clean Environment That Matches the Production Configuration. ### SaaS Environment - [ ] I have Tested My Changes on cloud.dify.ai with a Clean Environment That Matches the Production Configuration --- **Summary**: This PR adds 7 new cutting-edge AI models to the OpenRouter provider and updates 1 existing model configuration, ensuring Dify users have access to the latest DeepSeek R1 reasoning models and Claude Opus 4 coding capabilities. All models are configured with appropriate pricing, context sizes, and feature flags according to OpenRouter's current specifications. --- <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 11:15:14 -05:00
yindo closed this issue 2026-02-16 11:15:14 -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#1922
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?