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-33be0d612b9f1153b86f53e95bf7c571af2f1e466bda2330b632e6c05832e2a6.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/groqcloud%2Fgroqcloud-8bf31041292f851076489c3ac1270d06c49b995225d91cf5de2288a4bcfa8c29.yml

src/groq/resources/chat/completions.py

@@ -60,6 +60,7 @@ def create(
         functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
@@ -117,10 +118,14 @@ def create(
               probabilities of the output tokens or not. If true, returns the log
               probabilities of each output token returned in the `content` of `message`.
 
-          max_tokens: The maximum number of tokens that can be generated in the chat completion. The
+          max_completion_tokens: The maximum number of tokens that can be generated in the chat completion. The
               total length of input tokens and generated tokens is limited by the model's
               context length.
 
+          max_tokens: Deprecated in favor of `max_completion_tokens`. The maximum number of tokens
+              that can be generated in the chat completion. The total length of input tokens
+              and generated tokens is limited by the model's context length.
+
           n: How many chat completion choices to generate for each input message. Note that
               the current moment, only n=1 is supported. Other values will result in a 400
               response.
@@ -209,6 +214,7 @@ def create(
                     "functions": functions,
                     "logit_bias": logit_bias,
                     "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
                     "max_tokens": max_tokens,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
@@ -264,6 +270,7 @@ async def create(
         functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
@@ -321,10 +328,14 @@ async def create(
               probabilities of the output tokens or not. If true, returns the log
               probabilities of each output token returned in the `content` of `message`.
 
-          max_tokens: The maximum number of tokens that can be generated in the chat completion. The
+          max_completion_tokens: The maximum number of tokens that can be generated in the chat completion. The
               total length of input tokens and generated tokens is limited by the model's
               context length.
 
+          max_tokens: Deprecated in favor of `max_completion_tokens`. The maximum number of tokens
+              that can be generated in the chat completion. The total length of input tokens
+              and generated tokens is limited by the model's context length.
+
           n: How many chat completion choices to generate for each input message. Note that
               the current moment, only n=1 is supported. Other values will result in a 400
               response.
@@ -413,6 +424,7 @@ async def create(
                     "functions": functions,
                     "logit_bias": logit_bias,
                     "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
                     "max_tokens": max_tokens,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,

src/groq/types/chat/completion_create_params.py

@@ -64,13 +64,20 @@ class CompletionCreateParams(TypedDict, total=False):
     probabilities of each output token returned in the `content` of `message`.
     """
 
-    max_tokens: Optional[int]
+    max_completion_tokens: Optional[int]
     """The maximum number of tokens that can be generated in the chat completion.
 
     The total length of input tokens and generated tokens is limited by the model's
     context length.
     """
 
+    max_tokens: Optional[int]
+    """
+    Deprecated in favor of `max_completion_tokens`. The maximum number of tokens
+    that can be generated in the chat completion. The total length of input tokens
+    and generated tokens is limited by the model's context length.
+    """
+
     n: Optional[int]
     """How many chat completion choices to generate for each input message.
 

tests/api_resources/chat/test_completions.py

@@ -52,6 +52,7 @@ def test_method_create_with_all_params(self, client: Groq) -> None:
             ],
             logit_bias={"foo": 0},
             logprobs=True,
+            max_completion_tokens=0,
             max_tokens=0,
             n=1,
             parallel_tool_calls=True,
@@ -154,6 +155,7 @@ async def test_method_create_with_all_params(self, async_client: AsyncGroq) -> N
             ],
             logit_bias={"foo": 0},
             logprobs=True,
+            max_completion_tokens=0,
             max_tokens=0,
             n=1,
             parallel_tool_calls=True,