diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
index 098494ff9..cc0bb7a11 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
@@ -76,3 +76,4 @@ pricing:
   output: '0.12'
   unit: '0.001'
   currency: RMB
+deprecated: true
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
index 9d0d3f8db..4af4822e8 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
@@ -10,7 +10,7 @@ features:
   - stream-tool-call
 model_properties:
   mode: chat
-  context_size: 8000
+  context_size: 32000
 parameter_rules:
   - name: temperature
     use_template: temperature
@@ -26,7 +26,7 @@ parameter_rules:
     type: int
     default: 2000
     min: 1
-    max: 2000
+    max: 8192
     help:
       zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
       en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
index 9089e5725..529a29b1b 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
@@ -10,7 +10,7 @@ features:
   - stream-tool-call
 model_properties:
   mode: chat
-  context_size: 131072
+  context_size: 128000
 parameter_rules:
   - name: temperature
     use_template: temperature
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
index 215c9ec5f..a0c4ba682 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
@@ -10,7 +10,7 @@ features:
   - stream-tool-call
 model_properties:
   mode: chat
-  context_size: 8000
+  context_size: 128000
 parameter_rules:
   - name: temperature
     use_template: temperature
@@ -26,7 +26,7 @@ parameter_rules:
     type: int
     default: 2000
     min: 1
-    max: 2000
+    max: 8192
     help:
       zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
       en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.