feat(api): api update

.stats.yml

@@ -1,2 +1,2 @@
 configured_endpoints: 7
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/groqcloud%2Fgroqcloud-b33d3547dd14387df0951ff9638519f7c1a125db265801f63e9136cfa5e4578b.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/groqcloud%2Fgroqcloud-33be0d612b9f1153b86f53e95bf7c571af2f1e466bda2330b632e6c05832e2a6.yml

src/groq/resources/chat/completions.py

@@ -66,7 +66,7 @@ def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["on_demand", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: Optional[bool] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -144,6 +144,12 @@ def create(
               the same result. Determinism is not guaranteed, and you should refer to the
               `system_fingerprint` response parameter to monitor changes in the backend.
 
+          service_tier: The service tier to use for the request. Defaults to `on_demand`.
+
+              - `auto` will automatically select the highest tier available within the rate
+                limits of your organization.
+              - `flex` uses the flex tier, which will succeed or fail quickly.
+
           stop: Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
@@ -264,7 +270,7 @@ async def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["on_demand", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: Optional[bool] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -342,6 +348,12 @@ async def create(
               the same result. Determinism is not guaranteed, and you should refer to the
               `system_fingerprint` response parameter to monitor changes in the backend.
 
+          service_tier: The service tier to use for the request. Defaults to `on_demand`.
+
+              - `auto` will automatically select the highest tier available within the rate
+                limits of your organization.
+              - `flex` uses the flex tier, which will succeed or fail quickly.
+
           stop: Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 

src/groq/types/chat/completion_create_params.py

@@ -106,7 +106,13 @@ class CompletionCreateParams(TypedDict, total=False):
     `system_fingerprint` response parameter to monitor changes in the backend.
     """
 
-    service_tier: Optional[Literal["on_demand", "flex"]]
+    service_tier: Optional[Literal["auto", "on_demand", "flex"]]
+    """The service tier to use for the request. Defaults to `on_demand`.
+
+    - `auto` will automatically select the highest tier available within the rate
+      limits of your organization.
+    - `flex` uses the flex tier, which will succeed or fail quickly.
+    """
 
     stop: Union[Optional[str], List[str], None]
     """Up to 4 sequences where the API will stop generating further tokens.

tests/api_resources/chat/test_completions.py

@@ -58,7 +58,7 @@ def test_method_create_with_all_params(self, client: Groq) -> None:
             presence_penalty=-2,
             response_format={"type": "text"},
             seed=0,
-            service_tier="on_demand",
+            service_tier="auto",
             stop="\n",
             stream=True,
             temperature=1,
@@ -160,7 +160,7 @@ async def test_method_create_with_all_params(self, async_client: AsyncGroq) -> N
             presence_penalty=-2,
             response_format={"type": "text"},
             seed=0,
-            service_tier="on_demand",
+            service_tier="auto",
             stop="\n",
             stream=True,
             temperature=1,