chore(doc): clarify service tier default value (#1496)

.stats.yml

@@ -1,2 +1,2 @@
 configured_endpoints: 64
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-8fe357c6b5a425d810d731e4102a052d8e38c5e2d66950e6de1025415160bf88.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-3a69e1cc9e1efda3fb82d0fb35961749f886a87594dae9d8d2aa5c60f157f5d2.yml

src/openai/resources/chat/completions.py

@@ -169,7 +169,8 @@ def create(
 
               - If set to 'auto', the system will utilize scale tier credits until they are
                 exhausted.
-              - If set to 'default', the request will be processed in the shared cluster.
+              - If set to 'default', the request will be processed using the default service
+                tier with a lower uptime SLA and no latency guarentee.
 
               When this parameter is set, the response body will include the `service_tier`
               utilized.
@@ -363,7 +364,8 @@ def create(
 
               - If set to 'auto', the system will utilize scale tier credits until they are
                 exhausted.
-              - If set to 'default', the request will be processed in the shared cluster.
+              - If set to 'default', the request will be processed using the default service
+                tier with a lower uptime SLA and no latency guarentee.
 
               When this parameter is set, the response body will include the `service_tier`
               utilized.
@@ -550,7 +552,8 @@ def create(
 
               - If set to 'auto', the system will utilize scale tier credits until they are
                 exhausted.
-              - If set to 'default', the request will be processed in the shared cluster.
+              - If set to 'default', the request will be processed using the default service
+                tier with a lower uptime SLA and no latency guarentee.
 
               When this parameter is set, the response body will include the `service_tier`
               utilized.
@@ -812,7 +815,8 @@ async def create(
 
               - If set to 'auto', the system will utilize scale tier credits until they are
                 exhausted.
-              - If set to 'default', the request will be processed in the shared cluster.
+              - If set to 'default', the request will be processed using the default service
+                tier with a lower uptime SLA and no latency guarentee.
 
               When this parameter is set, the response body will include the `service_tier`
               utilized.
@@ -1006,7 +1010,8 @@ async def create(
 
               - If set to 'auto', the system will utilize scale tier credits until they are
                 exhausted.
-              - If set to 'default', the request will be processed in the shared cluster.
+              - If set to 'default', the request will be processed using the default service
+                tier with a lower uptime SLA and no latency guarentee.
 
               When this parameter is set, the response body will include the `service_tier`
               utilized.
@@ -1193,7 +1198,8 @@ async def create(
 
               - If set to 'auto', the system will utilize scale tier credits until they are
                 exhausted.
-              - If set to 'default', the request will be processed in the shared cluster.
+              - If set to 'default', the request will be processed using the default service
+                tier with a lower uptime SLA and no latency guarentee.
 
               When this parameter is set, the response body will include the `service_tier`
               utilized.

src/openai/types/chat/completion_create_params.py

@@ -153,7 +153,8 @@ class CompletionCreateParamsBase(TypedDict, total=False):
 
     - If set to 'auto', the system will utilize scale tier credits until they are
       exhausted.
-    - If set to 'default', the request will be processed in the shared cluster.
+    - If set to 'default', the request will be processed using the default service
+      tier with a lower uptime SLA and no latency guarentee.
 
     When this parameter is set, the response body will include the `service_tier`
     utilized.