Claude 3.5 Sonnet is limited to 4096 tokens - should be 8192

Describe the bug

When invoking converse with maxTokens > 4096, it tells me that I cant. But Clause Sonnet 3.5 has a token limit of 8192. I've tested to use the anthropic SDK instead of boto3 and that works.

Expected Behavior

Should work with maxTokens up to 8192.

Current Behavior

client = boto3.client(
    'bedrock-runtime',
    region_name=AWS_REGION,
    aws_access_key_id=AWS_ACCESS_KEY_ID,
    aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
)

response = client.converse(
    modelId=f"arn:aws:bedrock:{AWS_REGION}:***:inference-profile/eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
    messages=[{"role": "user", "content": [{"text": "Hello, world"}]}],
    inferenceConfig={
        'maxTokens': 8192,
    },
)
---------------------------------------------------------------------------
ValidationException                       Traceback (most recent call last)
Cell In[19], line 8
      1 client = boto3.client(
      2     'bedrock-runtime',
      3     region_name=AWS_REGION,
      4     aws_access_key_id=AWS_ACCESS_KEY_ID,
      5     aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
      6 )
----> 8 response = client.converse(
      9     modelId="arn:aws:bedrock:eu-west-1:760878568205:inference-profile/eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
     10     messages=[{"role": "user", "content": [{"text": "Hello, world"}]}],
     11     inferenceConfig={
     12         'maxTokens': 8192,
     13     },
     14 )

File /usr/local/lib/python3.12/site-packages/botocore/client.py:569, in ClientCreator._create_api_method.<locals>._api_call(self, *args, **kwargs)
    565     raise TypeError(
    566         f"{py_operation_name}() only accepts keyword arguments."
    567     )
    568 # The "self" in this scope is referring to the BaseClient.
--> 569 return self._make_api_call(operation_name, kwargs)

File /usr/local/lib/python3.12/site-packages/botocore/client.py:1023, in BaseClient._make_api_call(self, operation_name, api_params)
   1019     error_code = error_info.get("QueryErrorCode") or error_info.get(
   1020         "Code"
   1021     )
   1022     error_class = self.exceptions.from_code(error_code)
-> 1023     raise error_class(parsed_response, operation_name)
   1024 else:
   1025     return parsed_response

ValidationException: An error occurred (ValidationException) when calling the Converse operation: The maximum tokens you requested exceeds the model limit of 4096. Try again with a maximum tokens value that is lower than 4096.

Reproduction Steps

import boto3
from anthropic import AnthropicBedrock
from *** import AWS_ACCESS_KEY_ID, AWS_REGION, AWS_SECRET_ACCESS_KEY

client = AnthropicBedrock(
    aws_access_key=AWS_ACCESS_KEY_ID,
    aws_secret_key=AWS_SECRET_ACCESS_KEY,
    aws_region=AWS_REGION,
)

message = client.messages.create(
    model="eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
    max_tokens=8192,
    messages=[{"role": "user", "content": "Hello, world"}]
)
# This works perfectly fine

client = boto3.client(
    'bedrock-runtime',
    region_name=AWS_REGION,
    aws_access_key_id=AWS_ACCESS_KEY_ID,
    aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
)

response = client.converse(
    modelId=f"arn:aws:bedrock:{AWS_REGION}:***:inference-profile/eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
    messages=[{"role": "user", "content": [{"text": "Hello, world"}]}],
    inferenceConfig={
        'maxTokens': 8192,
    },
)
# ValidationException: An error occurred (ValidationException) when calling the Converse operation: The maximum tokens you requested exceeds the model limit of 4096. Try again with a maximum tokens value that is lower than 4096.

Possible Solution

No response

Additional Information/Context

No response

SDK version used

1.35.2

Environment details (OS name and version, etc.)

Linux and MacOs.

boto / boto3

Claude 3.5 Sonnet is limited to 4096 tokens - should be 8192 #4279