diff --git a/.env.example b/.env.example
index 00e909bc..999178ce 100644
--- a/.env.example
+++ b/.env.example
@@ -27,7 +27,7 @@ S3_REGION=us-east-1
 LLM_API_KEY=
 LLM_BASE_URL=https://factchat-cloud.mindlogic.ai/v1/gateway
 LLM_PRO_MODEL=gemini-3.1-pro-preview
-LLM_FLASH_MODEL=gemini-3.1-flash-lite-preview
+LLM_FLASH_MODEL=gemini-3.1-flash-lite
 LLM_FLASH_TEMPERATURE=0.4
 LLM_FLASH_MAX_TOKENS=512
 
diff --git a/ai/.env.example b/ai/.env.example
index 50a4b619..65866f0f 100644
--- a/ai/.env.example
+++ b/ai/.env.example
@@ -18,7 +18,7 @@ LLM_API_KEY=
 LLM_BASE_URL=https://factchat-cloud.mindlogic.ai/v1/gateway
 LLM_PRO_MODEL=gemini-3.1-pro-preview
 LLM_PRO_TEMPERATURE=0.2
-LLM_FLASH_MODEL=gemini-3.1-flash-lite-preview
+LLM_FLASH_MODEL=gemini-3.1-flash-lite
 LLM_FLASH_TEMPERATURE=0.4
 LLM_FLASH_MAX_TOKENS=512
 
diff --git a/ai/src/ai_server/config/settings.py b/ai/src/ai_server/config/settings.py
index b4a0fc2c..65f57120 100644
--- a/ai/src/ai_server/config/settings.py
+++ b/ai/src/ai_server/config/settings.py
@@ -47,7 +47,7 @@ class Settings(BaseSettings):
     llm_pro_temperature: float = 0.2
 
     # 꼬리질문용 Flash 모델 (저지연 < 3s)
-    llm_flash_model: str = "gemini-3.1-flash-lite-preview"
+    llm_flash_model: str = "gemini-3.1-flash-lite"
     llm_flash_temperature: float = 0.4
     llm_flash_max_tokens: int = 512
 
diff --git a/docker-compose.yml b/docker-compose.yml
index c28e95f6..44742b60 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -87,7 +87,7 @@ services:
       LLM_API_KEY: ${LLM_API_KEY:-}
       LLM_BASE_URL: ${LLM_BASE_URL:-https://factchat-cloud.mindlogic.ai/v1/gateway}
       LLM_PRO_MODEL: ${LLM_PRO_MODEL:-gemini-3.1-pro-preview}
-      LLM_FLASH_MODEL: ${LLM_FLASH_MODEL:-gemini-3.1-flash-lite-preview}
+      LLM_FLASH_MODEL: ${LLM_FLASH_MODEL:-gemini-3.1-flash-lite}
       LLM_FLASH_TEMPERATURE: ${LLM_FLASH_TEMPERATURE:-0.4}
       LLM_FLASH_MAX_TOKENS: ${LLM_FLASH_MAX_TOKENS:-512}
       # AI → Core 내부 API. 같은 compose 네트워크의 backend 서비스로 직접 라우팅.
diff --git a/docs/environment.md b/docs/environment.md
index 2aa8e85f..11064f0e 100644
--- a/docs/environment.md
+++ b/docs/environment.md
@@ -97,7 +97,7 @@ LLM_API_KEY=                      # 학교 발급 키
 LLM_BASE_URL=https://factchat-cloud.mindlogic.ai/v1/gateway
 LLM_PRO_MODEL=gemini-3.1-pro-preview
 LLM_PRO_TEMPERATURE=0.2
-LLM_FLASH_MODEL=gemini-3.1-flash-lite-preview   # 꼬리질문(US-19) 저지연 모델
+LLM_FLASH_MODEL=gemini-3.1-flash-lite   # 꼬리질문(US-19) 저지연 모델
 LLM_FLASH_TEMPERATURE=0.4
 LLM_FLASH_MAX_TOKENS=512