Feat: add TokenPony model provider (#9932)

### What problem does this PR solve?

Add TokenPony as a LLM provider

Co-authored-by: huangzl <huangzl@shinemo.com>

conf/llm_factories.json

@@ -219,6 +219,70 @@
                 }
             ]
         },
+        {
+            "name": "TokenPony",
+            "logo": "",
+            "tags": "LLM",
+            "status": "1",
+            "llm": [
+                {
+                    "llm_name": "qwen3-8b",
+                    "tags": "LLM,CHAT,131k",
+                    "max_tokens": 131000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "deepseek-v3-0324",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-32b",
+                    "tags": "LLM,CHAT,131k",
+                    "max_tokens": 131000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "kimi-k2-instruct",
+                    "tags": "LLM,CHAT,128K",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "deepseek-r1-0528",
+                    "tags": "LLM,CHAT,164k",
+                    "max_tokens": 164000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-coder-480b",
+                    "tags": "LLM,CHAT,1024k",
+                    "max_tokens": 1024000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "glm-4.5",
+                    "tags": "LLM,CHAT,131K",
+                    "max_tokens": 131000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "deepseek-v3.1",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                }
+            ]
+        },
         {
             "name": "Tongyi-Qianwen",
             "logo": "",

rag/llm/chat_model.py

@@ -1356,6 +1356,14 @@ class Ai302Chat(Base):
         super().__init__(key, model_name, base_url, **kwargs)
 
 
+class TokenPonyChat(Base):
+    _FACTORY_NAME = "TokenPony"
+
+    def __init__(self, key, model_name, base_url="https://ragflow.vip-api.tokenpony.cn/v1", **kwargs):
+        if not base_url:
+            base_url = "https://ragflow.vip-api.tokenpony.cn/v1"
+
+            
 class MeituanChat(Base):
     _FACTORY_NAME = "Meituan"
 

web/src/constants/llm.ts

@@ -54,6 +54,7 @@ export enum LLMFactory {
   DeepInfra = 'DeepInfra',
   Grok = 'Grok',
   XAI = 'xAI',
+  TokenPony = 'TokenPony',
   Meituan = 'Meituan',
 }
 
@@ -114,5 +115,6 @@ export const IconMap = {
   [LLMFactory.DeepInfra]: 'deepinfra',
   [LLMFactory.Grok]: 'grok',
   [LLMFactory.XAI]: 'xai',
+  [LLMFactory.TokenPony]: 'token-pony',
   [LLMFactory.Meituan]: 'longcat',
 };

web/src/pages/user-setting/setting-model/ollama-modal/index.tsx

@@ -37,6 +37,7 @@ const llmFactoryToUrlMap = {
     'https://huggingface.co/docs/text-embeddings-inference/quick_tour',
   [LLMFactory.GPUStack]: 'https://docs.gpustack.ai/latest/quickstart',
   [LLMFactory.VLLM]: 'https://docs.vllm.ai/en/latest/',
+  [LLMFactory.TokenPony]: 'https://docs.tokenpony.cn/#/',
 };
 type LlmFactory = keyof typeof llmFactoryToUrlMap;