diff --git a/.env.example b/.env.example
index 3660838..2d16c1c 100644
--- a/.env.example
+++ b/.env.example
@@ -13,3 +13,10 @@ CREATE_IMAGE_MODEL=imagen-3.0-generate-002
 UPLOAD_PROVIDER=smms
 SMMS_SECRET_TOKEN=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 ##########################################################################
+#########################stream_optimizer 相关配置########################
+STREAM_MIN_DELAY=0.016
+STREAM_MAX_DELAY=0.024
+STREAM_SHORT_TEXT_THRESHOLD=10
+STREAM_LONG_TEXT_THRESHOLD=50
+STREAM_CHUNK_SIZE=5
+##########################################################################
diff --git a/README.md b/README.md
index 1b9fa29..9f51d54 100644
--- a/README.md
+++ b/README.md
@@ -76,6 +76,13 @@
     # 图片上传配置
     UPLOAD_PROVIDER="smms"  # 图片上传提供商，目前支持smms
     SMMS_SECRET_TOKEN="your-smms-token"  # SM.MS图床的API Token
+
+    # stream_optimizer 相关配置
+    STREAM_MIN_DELAY=0.016
+    STREAM_MAX_DELAY=0.024
+    STREAM_SHORT_TEXT_THRESHOLD=10
+    STREAM_LONG_TEXT_THRESHOLD=50
+    STREAM_CHUNK_SIZE=5
     ```
 
    ### 配置说明
@@ -136,6 +143,24 @@
       - 用途: 用于图片上传到 SM.MS 图床
       - 获取方式: 需要在 SM.MS 官网注册并获取
 
+   #### 流式输出优化配置
+
+    - `STREAM_MIN_DELAY`: 最小延迟时间
+      - 默认值: `0.016`（秒）
+      - 说明: 长文本输出时使用的最小延迟时间，值越小输出速度越快
+    - `STREAM_MAX_DELAY`: 最大延迟时间
+      - 默认值: `0.024`（秒）
+      - 说明: 短文本输出时使用的最大延迟时间，值越大输出速度越慢
+    - `STREAM_SHORT_TEXT_THRESHOLD`: 短文本阈值
+      - 默认值: `10`（字符）
+      - 说明: 小于此长度的文本被视为短文本，将使用最大延迟输出
+    - `STREAM_LONG_TEXT_THRESHOLD`: 长文本阈值
+      - 默认值: `50`（字符）
+      - 说明: 大于此长度的文本被视为长文本，将使用最小延迟并分块输出
+    - `STREAM_CHUNK_SIZE`: 长文本分块大小
+      - 默认值: `5`（字符）
+      - 说明: 长文本分块输出时，每个块的大小
+
 ### ▶️ 运行
 
 #### 使用 Docker (推荐)
diff --git a/app/core/config.py b/app/core/config.py
index 7b9ac09..7faa49c 100644
--- a/app/core/config.py
+++ b/app/core/config.py
@@ -17,6 +17,13 @@ class Settings(BaseSettings):
     UPLOAD_PROVIDER: str = "smms"
     SMMS_SECRET_TOKEN: str = ""
     TEST_MODEL: str = "gemini-1.5-flash"
+    
+    # 流式输出优化器配置
+    STREAM_MIN_DELAY: float = 0.016
+    STREAM_MAX_DELAY: float = 0.024
+    STREAM_SHORT_TEXT_THRESHOLD: int = 10
+    STREAM_LONG_TEXT_THRESHOLD: int = 50
+    STREAM_CHUNK_SIZE: int = 5
 
     def __init__(self):
         super().__init__()
diff --git a/app/services/chat/stream_optimizer.py b/app/services/chat/stream_optimizer.py
index c3f0ef5..cdf3010 100644
--- a/app/services/chat/stream_optimizer.py
+++ b/app/services/chat/stream_optimizer.py
@@ -4,6 +4,7 @@ import asyncio
 import math
 from typing import Any, List, AsyncGenerator, Callable
 from app.core.logger import get_openai_logger, get_gemini_logger
+from app.core.config import settings
 
 logger_openai = get_openai_logger()
 logger_gemini = get_gemini_logger()
@@ -112,5 +113,20 @@ class StreamOptimizer:
 
 
 # 创建默认的优化器实例，可以直接导入使用
-openai_optimizer = StreamOptimizer(logger=logger_openai)
-gemini_optimizer = StreamOptimizer(logger=logger_gemini)
+openai_optimizer = StreamOptimizer(
+    logger=logger_openai,
+    min_delay=settings.STREAM_MIN_DELAY,
+    max_delay=settings.STREAM_MAX_DELAY,
+    short_text_threshold=settings.STREAM_SHORT_TEXT_THRESHOLD,
+    long_text_threshold=settings.STREAM_LONG_TEXT_THRESHOLD,
+    chunk_size=settings.STREAM_CHUNK_SIZE
+)
+
+gemini_optimizer = StreamOptimizer(
+    logger=logger_gemini,
+    min_delay=settings.STREAM_MIN_DELAY,
+    max_delay=settings.STREAM_MAX_DELAY,
+    short_text_threshold=settings.STREAM_SHORT_TEXT_THRESHOLD,
+    long_text_threshold=settings.STREAM_LONG_TEXT_THRESHOLD,
+    chunk_size=settings.STREAM_CHUNK_SIZE
+)