diff --git a/api/core/constant/llm_constant.py b/api/core/constant/llm_constant.py
index 6879ec5b06..397a3d4c8f 100644
--- a/api/core/constant/llm_constant.py
+++ b/api/core/constant/llm_constant.py
@@ -4,6 +4,7 @@ models = {
     'gpt-4': 'openai',  # 8,192 tokens
     'gpt-4-32k': 'openai',  # 32,768 tokens
     'gpt-3.5-turbo': 'openai',  # 4,096 tokens
+    'gpt-3.5-turbo-16k': 'openai',  # 16384 tokens
     'text-davinci-003': 'openai',  # 4,097 tokens
     'text-davinci-002': 'openai',  # 4,097 tokens
     'text-curie-001': 'openai',  # 2,049 tokens
@@ -16,6 +17,7 @@ max_context_token_length = {
     'gpt-4': 8192,
     'gpt-4-32k': 32768,
     'gpt-3.5-turbo': 4096,
+    'gpt-3.5-turbo-16k': 16384,
     'text-davinci-003': 4097,
     'text-davinci-002': 4097,
     'text-curie-001': 2049,
@@ -29,11 +31,13 @@ models_by_mode = {
         'gpt-4',  # 8,192 tokens
         'gpt-4-32k',  # 32,768 tokens
         'gpt-3.5-turbo',  # 4,096 tokens
+        'gpt-3.5-turbo-16k',  # 16,384 tokens
     ],
     'completion': [
         'gpt-4',  # 8,192 tokens
         'gpt-4-32k',  # 32,768 tokens
         'gpt-3.5-turbo',  # 4,096 tokens
+        'gpt-3.5-turbo-16k',  # 16,384 tokens
         'text-davinci-003',  # 4,097 tokens
         'text-davinci-002'  # 4,097 tokens
         'text-curie-001',  # 2,049 tokens
@@ -57,9 +61,13 @@ model_prices = {
         'completion': Decimal('0.12')
     },
     'gpt-3.5-turbo': {
-        'prompt': Decimal('0.002'),
+        'prompt': Decimal('0.0015'),
         'completion': Decimal('0.002')
     },
+    'gpt-3.5-turbo-16k': {
+        'prompt': Decimal('0.003'),
+        'completion': Decimal('0.004')
+    },
     'text-davinci-003': {
         'prompt': Decimal('0.02'),
         'completion': Decimal('0.02')
@@ -77,7 +85,7 @@ model_prices = {
         'completion': Decimal('0.0004')
     },
     'text-embedding-ada-002': {
-        'usage': Decimal('0.0004'),
+        'usage': Decimal('0.0001'),
     }
 }
 
diff --git a/api/core/llm/provider/azure_provider.py b/api/core/llm/provider/azure_provider.py
index d87ab761d3..c64e785215 100644
--- a/api/core/llm/provider/azure_provider.py
+++ b/api/core/llm/provider/azure_provider.py
@@ -95,7 +95,8 @@ class AzureProvider(BaseProvider):
 
             if not models:
                 raise ValidateFailedError("Please add deployments for 'text-davinci-003', "
-                                          "'gpt-3.5-turbo', 'text-embedding-ada-002'.")
+                                          "'gpt-3.5-turbo', 'text-embedding-ada-002' (required) "
+                                          "and 'gpt-4', 'gpt-35-turbo-16k' (optional).")
 
             fixed_model_ids = [
                 'text-davinci-003',
diff --git a/web/app/components/app/configuration/config-model/index.tsx b/web/app/components/app/configuration/config-model/index.tsx
index 7a9601e39b..15a3754e1d 100644
--- a/web/app/components/app/configuration/config-model/index.tsx
+++ b/web/app/components/app/configuration/config-model/index.tsx
@@ -26,8 +26,10 @@ export type IConifgModelProps = {
 
 const options = [
   { id: 'gpt-3.5-turbo', name: 'gpt-3.5-turbo', type: AppType.chat },
+  { id: 'gpt-3.5-turbo-16k', name: 'gpt-3.5-turbo-16k', type: AppType.chat },
   { id: 'gpt-4', name: 'gpt-4', type: AppType.chat }, // 8k version
   { id: 'gpt-3.5-turbo', name: 'gpt-3.5-turbo', type: AppType.completion },
+  { id: 'gpt-3.5-turbo-16k', name: 'gpt-3.5-turbo-16k', type: AppType.completion },
   { id: 'text-davinci-003', name: 'text-davinci-003', type: AppType.completion },
   { id: 'gpt-4', name: 'gpt-4', type: AppType.completion }, // 8k version
 ]