diff --git a/server/routers/chat_router.py b/server/routers/chat_router.py
index b10945c4..0d8058a3 100644
--- a/server/routers/chat_router.py
+++ b/server/routers/chat_router.py
@@ -118,6 +118,7 @@ def chat_post(
 
 @chat.post("/call")
 async def call(query: str = Body(...), meta: dict = Body(None)):
+    meta = meta or {}
     model = select_model(model_provider=meta.get("model_provider"), model_name=meta.get("model_name"))
     async def predict_async(query):
         loop = asyncio.get_event_loop()
@@ -129,7 +130,7 @@ async def call(query: str = Body(...), meta: dict = Body(None)):
     return {"response": response.content}
 
 @chat.post("/call_lite")
-async def call(query: str = Body(...), meta: dict = Body(None)):
+async def call_lite(query: str = Body(...), meta: dict = Body(None)):
     meta = meta or {}
     async def predict_async(query):
         loop = asyncio.get_event_loop()
diff --git a/src/config/__init__.py b/src/config/__init__.py
index da6bcac8..764778d9 100644
--- a/src/config/__init__.py
+++ b/src/config/__init__.py
@@ -99,11 +99,12 @@ class Config(SimpleConfig):
         except FileNotFoundError:
             _models_private = {}
 
-        _models = {**_models, **_models_private}
+        # 修改为按照子元素合并
+        # _models = {**_models, **_models_private}
 
-        self.model_names = _models["MODEL_NAMES"]
-        self.embed_model_names = _models["EMBED_MODEL_INFO"]
-        self.reranker_names = _models["RERANKER_LIST"]
+        self.model_names = {**_models["MODEL_NAMES"], **_models_private["MODEL_NAMES"]}
+        self.embed_model_names = {**_models["EMBED_MODEL_INFO"], **_models_private["EMBED_MODEL_INFO"]}
+        self.reranker_names = {**_models["RERANKER_LIST"], **_models_private["RERANKER_LIST"]}
 
     def _save_models_to_file(self):
         _models = {
diff --git a/src/models/__init__.py b/src/models/__init__.py
index b796a52b..19867377 100644
--- a/src/models/__init__.py
+++ b/src/models/__init__.py
@@ -1,5 +1,5 @@
 import os
-
+import traceback
 from src import config
 from src.utils.logging_config import logger
 from src.models.chat_model import OpenAIBase
@@ -14,33 +14,23 @@ def select_model(model_provider=None, model_name=None):
 
     logger.info(f"Selecting model from `{model_provider}` with `{model_name}`")
 
-    if model_provider in [
-        "deepseek",
-        "ark",
-        "siliconflow",
-        "zhipu",
-        "lingyiwanwu",
-        "together.ai",
-    ]:
-        return OpenAIBase(
-            api_key=os.getenv(model_info["env"][0]),
-            base_url=model_info["base_url"],
-            model_name=model_name,
-        )
 
-    elif model_provider == "qianfan":
+    if model_provider is None:
+        raise ValueError("Model provider not specified, please modify `model_provider` in `src/config/base.yaml`")
+
+    if model_provider == "qianfan":
         from src.models.chat_model import Qianfan
         return Qianfan(model_name)
 
-    elif model_provider == "dashscope":
+    if model_provider == "dashscope":
         from src.models.chat_model import DashScope
         return DashScope(model_name)
 
-    elif model_provider == "openai":
+    if model_provider == "openai":
         from src.models.chat_model import OpenModel
         return OpenModel(model_name)
 
-    elif model_provider == "custom":
+    if model_provider == "custom":
         model_info = next((x for x in config.custom_models if x["custom_id"] == model_name), None)
         if model_info is None:
             raise ValueError(f"Model {model_name} not found in custom models")
@@ -48,7 +38,13 @@ def select_model(model_provider=None, model_name=None):
         from src.models.chat_model import CustomModel
         return CustomModel(model_info)
 
-    elif model_provider is None:
-        raise ValueError("Model provider not specified, please modify `model_provider` in `src/config/base.yaml`")
-    else:
-        raise ValueError(f"Model provider {model_provider} not supported")
+    # 其他模型，默认使用OpenAIBase
+    try:
+        model = OpenAIBase(
+            api_key=os.getenv(model_info["env"][0]),
+            base_url=model_info["base_url"],
+            model_name=model_name,
+        )
+        return model
+    except Exception as e:
+        raise ValueError(f"Model provider {model_provider} load failed, {e} \n {traceback.format_exc()}")
diff --git a/src/static/models.yaml b/src/static/models.yaml
index 9a41c7a9..037c6d46 100644
--- a/src/static/models.yaml
+++ b/src/static/models.yaml
@@ -99,6 +99,7 @@ MODEL_NAMES:
       - doubao-1-5-pro-32k-250115
       - doubao-1-5-lite-32k-250115
       - deepseek-r1-250120
+
   lingyiwanwu:
     name: 零一万物
     url: https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B%E4%B8%8E%E8%AE%A1%E8%B4%B9
@@ -109,6 +110,24 @@ MODEL_NAMES:
     models:
       - yi-lightning
 
+  openrouter:
+    name: OpenRouter
+    url: https://openrouter.ai/models
+    base_url: https://openrouter.ai/api/v1
+    default: openai/gpt-4o
+    env:
+      - OPENROUTER_API_KEY
+    models:
+      - openai/gpt-4o
+      - openai/gpt-4o-mini
+      - google/gemini-2.5-pro-exp-03-25:free
+      - x-ai/grok-3-beta
+      - meta-llama/llama-4-maverick
+      - meta-llama/llama-4-maverick:free
+      - anthropic/claude-3.7-sonnet
+      - anthropic/claude-3.7-sonnet:thinking
+
+
 EMBED_MODEL_INFO:
   local/BAAI/bge-m3:
     name: BAAI/bge-m3
diff --git a/web/src/assets/pics/guides/how-to-add-models.png b/web/src/assets/pics/guides/how-to-add-models.png
new file mode 100644
index 00000000..26060f29
Binary files /dev/null and b/web/src/assets/pics/guides/how-to-add-models.png differ
diff --git a/web/src/assets/providers/default.png b/web/src/assets/providers/default.png
new file mode 100644
index 00000000..289f0d16
Binary files /dev/null and b/web/src/assets/providers/default.png differ
diff --git a/web/src/assets/providers/openrouterai.png b/web/src/assets/providers/openrouterai.png
new file mode 100644
index 00000000..6138661c
Binary files /dev/null and b/web/src/assets/providers/openrouterai.png differ
diff --git a/web/src/utils/modelIcon.js b/web/src/utils/modelIcon.js
index b0b0e35f..f9aea808 100644
--- a/web/src/utils/modelIcon.js
+++ b/web/src/utils/modelIcon.js
@@ -7,7 +7,8 @@ import zhipuIcon from '@/assets/providers/zhipuai.png'
 import siliconflowIcon from '@/assets/providers/siliconflow.png'
 import arkIcon from '@/assets/providers/ark.png'
 import lingyiwanwuIcon from '@/assets/providers/lingyiwanwu.png'
-
+import openrouterIcon from '@/assets/providers/openrouterai.png'
+import defaultIcon from '@/assets/providers/default.png'
 
 export const modelIcons = {
   openai: openaiIcon,
@@ -19,5 +20,7 @@ export const modelIcons = {
   siliconflow: siliconflowIcon,
   ark: arkIcon,
   'together.ai': togetherIcon,
-  lingyiwanwu: lingyiwanwuIcon
+  lingyiwanwu: lingyiwanwuIcon,
+  openrouter: openrouterIcon,
+  default: defaultIcon // 添加默认图标
 }
diff --git a/web/src/views/SettingView.vue b/web/src/views/SettingView.vue
index c8ba40df..bec90fc9 100644
--- a/web/src/views/SettingView.vue
+++ b/web/src/views/SettingView.vue
@@ -162,7 +162,7 @@
           <div class="card-header" @click="toggleExpand(item)">
             <!-- <div v-if="modelStatus[item]" class="success"></div> -->
             <div :class="{'model-icon': true, 'available': modelStatus[item]}">
-              <img :src="modelIcons[item]" alt="模型图标">
+              <img :src="modelIcons[item] || modelIcons.default" alt="模型图标">
             </div>
             <div class="model-title-container">
               <h3>{{ modelNames[item].name }}</h3>
@@ -203,7 +203,7 @@
         <div class="model-provider-card" v-for="(item, key) in notModelKeys" :key="key">
           <div class="card-header">
             <div class="model-icon">
-              <img :src="modelIcons[item]" alt="模型图标">
+              <img :src="modelIcons[item] || modelIcons.default" alt="模型图标">
             </div>
             <div class="model-title-container">
               <h3 style="font-weight: 400">{{ modelNames[item].name }}</h3>
@@ -266,7 +266,10 @@
           </div>
           <div v-if="providerConfig.allModels.length === 0" class="modal-no-models">
             <a-alert v-if="!modelStatus[providerConfig.provider]" type="warning" message="请在 src/.env 中配置对应的 APIKEY，并重新启动服务" />
-            <a-alert v-else type="warning" message="该提供商暂未适配获取模型列表的方法，如果需要添加模型，请在 src/static/models.private.yml 中添加。" />
+            <div v-else>
+              <a-alert type="warning" message="该提供商暂未适配获取模型列表的方法，如果需要添加模型，请在 src/static/models.private.yml 中添加。" />
+              <img src="@/assets/pics/guides/how-to-add-models.png" alt="添加模型指引" style="width: 100%; height: 100%;">
+            </div>
           </div>
         </div>
       </div>