diff --git a/servers/bwh-hk-cmi/litellm/README.md b/servers/bwh-hk-cmi/litellm/README.md
index 684d967..5dce8cc 100644
--- a/servers/bwh-hk-cmi/litellm/README.md
+++ b/servers/bwh-hk-cmi/litellm/README.md
@@ -3,4 +3,7 @@
 - 仅通过 Hong Kong CMI 节点的 Tailscale IPv4 地址监听；`LISTEN_IP` 不要填写公网地址或 `0.0.0.0`。
 - ADC、LiteLLM key 仅存放于 Arcane `.env`，不得提交 Git。
 - 默认监听端口为 `1049`；需要修改时设置 `LITELLM_PORT`。
+- 对外模型别名包括 `gemini-3.6-flash`、`gemini-3.5-flash-lite`、
+  `google/gemini-embedding-2` 和 `google/gemini-3.8-flash`；后两者仍通过
+  Vertex AI ADC 路由。
 - 后续 Vertex Anthropic 模型在 `config.yaml` 增加独立模型项。
diff --git a/servers/bwh-hk-cmi/litellm/config.yaml b/servers/bwh-hk-cmi/litellm/config.yaml
index 6a15498..84a9f79 100644
--- a/servers/bwh-hk-cmi/litellm/config.yaml
+++ b/servers/bwh-hk-cmi/litellm/config.yaml
@@ -12,5 +12,17 @@ model_list:
       vertex_project: os.environ/VERTEXAI_PROJECT
       vertex_location: os.environ/VERTEXAI_LOCATION
 
+  - model_name: google/gemini-embedding-2
+    litellm_params:
+      model: vertex_ai/gemini-embedding-2
+      vertex_project: os.environ/VERTEXAI_PROJECT
+      vertex_location: os.environ/VERTEXAI_LOCATION
+
+  - model_name: google/gemini-3.8-flash
+    litellm_params:
+      model: vertex_ai/gemini-3.8-flash
+      vertex_project: os.environ/VERTEXAI_PROJECT
+      vertex_location: os.environ/VERTEXAI_LOCATION
+
 general_settings:
   master_key: os.environ/LITELLM_MASTER_KEY