[PR #2365] [CLOSED] Add LlamaGate model provider #2424

Closed
opened 2026-02-16 11:16:56 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langgenius/dify-official-plugins/pull/2365
Author: @hkd987
Created: 1/5/2026
Status: Closed

Base: mainHead: add-llamagate-provider


📝 Commits (2)

  • d367d26 Add LlamaGate model provider
  • 522e51f Address PR review feedback

📊 Changes

27 files changed (+589 additions, -0 deletions)

View changed files

models/llamagate/.env.example (+4 -0)
models/llamagate/README.md (+43 -0)
models/llamagate/_assets/icon_l_en.svg (+3 -0)
models/llamagate/_assets/icon_s_en.svg (+3 -0)
models/llamagate/main.py (+6 -0)
models/llamagate/manifest.yaml (+37 -0)
models/llamagate/models/llm/_position.yaml (+12 -0)
models/llamagate/models/llm/codellama-7b.yaml (+26 -0)
models/llamagate/models/llm/deepseek-coder-6.7b.yaml (+26 -0)
models/llamagate/models/llm/deepseek-r1-7b-qwen.yaml (+27 -0)
models/llamagate/models/llm/deepseek-r1-8b.yaml (+27 -0)
models/llamagate/models/llm/dolphin3-8b.yaml (+27 -0)
models/llamagate/models/llm/llama-3.1-8b.yaml (+27 -0)
models/llamagate/models/llm/llama-3.2-3b.yaml (+27 -0)
models/llamagate/models/llm/llm.py (+30 -0)
models/llamagate/models/llm/mistral-7b-v0.3.yaml (+27 -0)
models/llamagate/models/llm/openthinker-7b.yaml (+27 -0)
models/llamagate/models/llm/qwen2.5-coder-7b.yaml (+27 -0)
models/llamagate/models/llm/qwen3-8b.yaml (+27 -0)
models/llamagate/models/llm/qwen3-vl-8b.yaml (+28 -0)

...and 7 more files

📄 Description

Add LlamaGate Model Provider

Adds LlamaGate as a new model provider plugin for Dify.

Provider Details

  • API: OpenAI-compatible (https://api.llamagate.dev/v1)
    • Auth: Bearer token via api_key credential

Models Included

LLM Models (12):

  • Llama 3.1 8B Instruct, Llama 3.2 3B
    • DeepSeek R1 8B, DeepSeek R1 Distill Qwen 7B
    • Qwen 3 8B, Mistral 7B v0.3
    • Qwen 2.5 Coder 7B, CodeLlama 7B, DeepSeek Coder 6.7B
    • Qwen 3 VL 8B (Vision), OpenThinker 7B, Dolphin 3 8B
      Embedding Models (2):
  • Nomic Embed Text
    • Qwen 3 Embedding 8B

Features

  • Competitive pricing ($0.02-$0.55 per 1M tokens)
    • All models are open-weights
    • Extends OAICompatLargeLanguageModel and OAICompatEmbeddingModel base classes

Checklist

  • Other Changes (Add New Models, Fix Model Parameters etc.)
  • - [x] I have Ensured dify_plugin is in requirements.txt

🔄 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/2365 **Author:** [@hkd987](https://github.com/hkd987) **Created:** 1/5/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `add-llamagate-provider` --- ### 📝 Commits (2) - [`d367d26`](https://github.com/langgenius/dify-official-plugins/commit/d367d26c931b9586f20b39c1666bfd561737e571) Add LlamaGate model provider - [`522e51f`](https://github.com/langgenius/dify-official-plugins/commit/522e51fc19c85af9c95387bec2e6dbfd461c2545) Address PR review feedback ### 📊 Changes **27 files changed** (+589 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `models/llamagate/.env.example` (+4 -0) ➕ `models/llamagate/README.md` (+43 -0) ➕ `models/llamagate/_assets/icon_l_en.svg` (+3 -0) ➕ `models/llamagate/_assets/icon_s_en.svg` (+3 -0) ➕ `models/llamagate/main.py` (+6 -0) ➕ `models/llamagate/manifest.yaml` (+37 -0) ➕ `models/llamagate/models/llm/_position.yaml` (+12 -0) ➕ `models/llamagate/models/llm/codellama-7b.yaml` (+26 -0) ➕ `models/llamagate/models/llm/deepseek-coder-6.7b.yaml` (+26 -0) ➕ `models/llamagate/models/llm/deepseek-r1-7b-qwen.yaml` (+27 -0) ➕ `models/llamagate/models/llm/deepseek-r1-8b.yaml` (+27 -0) ➕ `models/llamagate/models/llm/dolphin3-8b.yaml` (+27 -0) ➕ `models/llamagate/models/llm/llama-3.1-8b.yaml` (+27 -0) ➕ `models/llamagate/models/llm/llama-3.2-3b.yaml` (+27 -0) ➕ `models/llamagate/models/llm/llm.py` (+30 -0) ➕ `models/llamagate/models/llm/mistral-7b-v0.3.yaml` (+27 -0) ➕ `models/llamagate/models/llm/openthinker-7b.yaml` (+27 -0) ➕ `models/llamagate/models/llm/qwen2.5-coder-7b.yaml` (+27 -0) ➕ `models/llamagate/models/llm/qwen3-8b.yaml` (+27 -0) ➕ `models/llamagate/models/llm/qwen3-vl-8b.yaml` (+28 -0) _...and 7 more files_ </details> ### 📄 Description ## Add LlamaGate Model Provider Adds [LlamaGate](https://llamagate.dev) as a new model provider plugin for Dify. ### Provider Details - **API:** OpenAI-compatible (`https://api.llamagate.dev/v1`) - - **Auth:** Bearer token via `api_key` credential ### Models Included **LLM Models (12):** - Llama 3.1 8B Instruct, Llama 3.2 3B - - DeepSeek R1 8B, DeepSeek R1 Distill Qwen 7B - - Qwen 3 8B, Mistral 7B v0.3 - - Qwen 2.5 Coder 7B, CodeLlama 7B, DeepSeek Coder 6.7B - - Qwen 3 VL 8B (Vision), OpenThinker 7B, Dolphin 3 8B **Embedding Models (2):** - Nomic Embed Text - - Qwen 3 Embedding 8B ### Features - Competitive pricing ($0.02-$0.55 per 1M tokens) - - All models are open-weights - - Extends OAICompatLargeLanguageModel and OAICompatEmbeddingModel base classes ### Checklist - [x] Other Changes (Add New Models, Fix Model Parameters etc.) - [x] - [x] I have Ensured `dify_plugin` is in requirements.txt --- <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 11:16:56 -05:00
yindo closed this issue 2026-02-16 11:16:56 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify-official-plugins#2424