diff --git a/.release-please-manifest.json b/.release-please-manifest.json
index 52afe059d..fe87cd917 100644
--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -1,3 +1,3 @@
 {
-  ".": "0.42.0"
+  ".": "0.43.0"
 }
\ No newline at end of file
diff --git a/.stats.yml b/.stats.yml
index 9af3f652d..2595a1785 100644
--- a/.stats.yml
+++ b/.stats.yml
@@ -1,4 +1,4 @@
 configured_endpoints: 91
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/runloop-ai%2Frunloop-86c4a065b1820b26c7afd40bbc374e87dd5e9c2ffa0abad26e7fd4ebec1cf72b.yml
-openapi_spec_hash: 6c6a44548177464033f3c174c89ba06a
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/runloop-ai%2Frunloop-32aaecf1da425c37d534ed04df36003ab9d766a7755cd18f96541929a2a3ea59.yml
+openapi_spec_hash: e326c47b99943cbbab473fde3b257221
 config_hash: 421e8d0e71c7ef71fdfebede08ea7271
diff --git a/CHANGELOG.md b/CHANGELOG.md
index f5b4780ff..8cf3b9669 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,23 @@
 # Changelog
 
+## 0.43.0 (2025-06-14)
+
+Full Changelog: [v0.42.0...v0.43.0](https://github.com/runloopai/api-client-python/compare/v0.42.0...v0.43.0)
+
+### Features
+
+* **api:** api update ([695b29a](https://github.com/runloopai/api-client-python/commit/695b29a97bd2dcad3f90ee377ed0475a84ed1a2b))
+
+
+### Bug Fixes
+
+* **client:** correctly parse binary response | stream ([1d815d4](https://github.com/runloopai/api-client-python/commit/1d815d468db24142174fe536c05dcd3ec49ee03f))
+
+
+### Chores
+
+* **tests:** run tests in parallel ([fdeee42](https://github.com/runloopai/api-client-python/commit/fdeee42440c5df55af77cbad2423c7faab473dcd))
+
 ## 0.42.0 (2025-06-11)
 
 Full Changelog: [v0.41.0...v0.42.0](https://github.com/runloopai/api-client-python/compare/v0.41.0...v0.42.0)
diff --git a/pyproject.toml b/pyproject.toml
index c61d56fec..1f083a49a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "runloop_api_client"
-version = "0.42.0"
+version = "0.43.0"
 description = "The official Python library for the runloop API"
 dynamic = ["readme"]
 license = "MIT"
@@ -54,6 +54,7 @@ dev-dependencies = [
     "importlib-metadata>=6.7.0",
     "rich>=13.7.1",
     "nest_asyncio==1.6.0",
+    "pytest-xdist>=3.6.1",
 ]
 
 [tool.rye.scripts]
@@ -125,7 +126,7 @@ replacement = '[\1](https://github.com/runloopai/api-client-python/tree/main/\g<
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
-addopts = "--tb=short"
+addopts = "--tb=short -n auto"
 xfail_strict = true
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "session"
diff --git a/requirements-dev.lock b/requirements-dev.lock
index 1e04b71cc..3063be477 100644
--- a/requirements-dev.lock
+++ b/requirements-dev.lock
@@ -30,6 +30,8 @@ distro==1.8.0
 exceptiongroup==1.2.2
     # via anyio
     # via pytest
+execnet==2.1.1
+    # via pytest-xdist
 filelock==3.12.4
     # via virtualenv
 h11==0.14.0
@@ -72,7 +74,9 @@ pygments==2.18.0
 pyright==1.1.399
 pytest==8.3.3
     # via pytest-asyncio
+    # via pytest-xdist
 pytest-asyncio==0.24.0
+pytest-xdist==3.7.0
 python-dateutil==2.8.2
     # via time-machine
 pytz==2023.3.post1
diff --git a/src/runloop_api_client/_base_client.py b/src/runloop_api_client/_base_client.py
index bba4933f3..74864535d 100644
--- a/src/runloop_api_client/_base_client.py
+++ b/src/runloop_api_client/_base_client.py
@@ -1071,7 +1071,14 @@ def _process_response(
     ) -> ResponseT:
         origin = get_origin(cast_to) or cast_to
 
-        if inspect.isclass(origin) and issubclass(origin, BaseAPIResponse):
+        if (
+            inspect.isclass(origin)
+            and issubclass(origin, BaseAPIResponse)
+            # we only want to actually return the custom BaseAPIResponse class if we're
+            # returning the raw response, or if we're not streaming SSE, as if we're streaming
+            # SSE then `cast_to` doesn't actively reflect the type we need to parse into
+            and (not stream or bool(response.request.headers.get(RAW_RESPONSE_HEADER)))
+        ):
             if not issubclass(origin, APIResponse):
                 raise TypeError(f"API Response types must subclass {APIResponse}; Received {origin}")
 
@@ -1574,7 +1581,14 @@ async def _process_response(
     ) -> ResponseT:
         origin = get_origin(cast_to) or cast_to
 
-        if inspect.isclass(origin) and issubclass(origin, BaseAPIResponse):
+        if (
+            inspect.isclass(origin)
+            and issubclass(origin, BaseAPIResponse)
+            # we only want to actually return the custom BaseAPIResponse class if we're
+            # returning the raw response, or if we're not streaming SSE, as if we're streaming
+            # SSE then `cast_to` doesn't actively reflect the type we need to parse into
+            and (not stream or bool(response.request.headers.get(RAW_RESPONSE_HEADER)))
+        ):
             if not issubclass(origin, AsyncAPIResponse):
                 raise TypeError(f"API Response types must subclass {AsyncAPIResponse}; Received {origin}")
 
diff --git a/src/runloop_api_client/_version.py b/src/runloop_api_client/_version.py
index dee24268d..5c05630c7 100644
--- a/src/runloop_api_client/_version.py
+++ b/src/runloop_api_client/_version.py
@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "runloop_api_client"
-__version__ = "0.42.0"  # x-release-please-version
+__version__ = "0.43.0"  # x-release-please-version
diff --git a/src/runloop_api_client/resources/scenarios/scenarios.py b/src/runloop_api_client/resources/scenarios/scenarios.py
index 2ff71e2c8..f86bc4873 100644
--- a/src/runloop_api_client/resources/scenarios/scenarios.py
+++ b/src/runloop_api_client/resources/scenarios/scenarios.py
@@ -256,6 +256,7 @@ def update(
     def list(
         self,
         *,
+        benchmark_id: str | NotGiven = NOT_GIVEN,
         limit: int | NotGiven = NOT_GIVEN,
         name: str | NotGiven = NOT_GIVEN,
         starting_after: str | NotGiven = NOT_GIVEN,
@@ -266,12 +267,13 @@ def list(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> SyncScenariosCursorIDPage[ScenarioView]:
-        """List all Scenarios matching filter.
+        """
+        List all Scenarios matching filter.
 
         Args:
-          limit: The limit of items to return.
+          benchmark_id: Filter scenarios by benchmark ID.
 
-        Default is 20.
+          limit: The limit of items to return. Default is 20.
 
           name: Query for Scenarios with a given name.
 
@@ -295,6 +297,7 @@ def list(
                 timeout=timeout,
                 query=maybe_transform(
                     {
+                        "benchmark_id": benchmark_id,
                         "limit": limit,
                         "name": name,
                         "starting_after": starting_after,
@@ -679,6 +682,7 @@ async def update(
     def list(
         self,
         *,
+        benchmark_id: str | NotGiven = NOT_GIVEN,
         limit: int | NotGiven = NOT_GIVEN,
         name: str | NotGiven = NOT_GIVEN,
         starting_after: str | NotGiven = NOT_GIVEN,
@@ -689,12 +693,13 @@ def list(
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> AsyncPaginator[ScenarioView, AsyncScenariosCursorIDPage[ScenarioView]]:
-        """List all Scenarios matching filter.
+        """
+        List all Scenarios matching filter.
 
         Args:
-          limit: The limit of items to return.
+          benchmark_id: Filter scenarios by benchmark ID.
 
-        Default is 20.
+          limit: The limit of items to return. Default is 20.
 
           name: Query for Scenarios with a given name.
 
@@ -718,6 +723,7 @@ def list(
                 timeout=timeout,
                 query=maybe_transform(
                     {
+                        "benchmark_id": benchmark_id,
                         "limit": limit,
                         "name": name,
                         "starting_after": starting_after,
diff --git a/src/runloop_api_client/types/scenario_list_params.py b/src/runloop_api_client/types/scenario_list_params.py
index 26c4b5c79..917da6c94 100644
--- a/src/runloop_api_client/types/scenario_list_params.py
+++ b/src/runloop_api_client/types/scenario_list_params.py
@@ -8,6 +8,9 @@
 
 
 class ScenarioListParams(TypedDict, total=False):
+    benchmark_id: str
+    """Filter scenarios by benchmark ID."""
+
     limit: int
     """The limit of items to return. Default is 20."""
 
diff --git a/tests/api_resources/test_scenarios.py b/tests/api_resources/test_scenarios.py
index 7e77cd2a9..a7fa7a293 100644
--- a/tests/api_resources/test_scenarios.py
+++ b/tests/api_resources/test_scenarios.py
@@ -339,6 +339,7 @@ def test_method_list(self, client: Runloop) -> None:
     @parametrize
     def test_method_list_with_all_params(self, client: Runloop) -> None:
         scenario = client.scenarios.list(
+            benchmark_id="benchmark_id",
             limit=0,
             name="name",
             starting_after="starting_after",
@@ -762,6 +763,7 @@ async def test_method_list(self, async_client: AsyncRunloop) -> None:
     @parametrize
     async def test_method_list_with_all_params(self, async_client: AsyncRunloop) -> None:
         scenario = await async_client.scenarios.list(
+            benchmark_id="benchmark_id",
             limit=0,
             name="name",
             starting_after="starting_after",