diff --git a/.release-please-manifest.json b/.release-please-manifest.json
index 127ac87b..6a37fe2d 100644
--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -1,3 +1,3 @@
 {
-  ".": "4.0.0"
+  ".": "4.0.1"
 }
\ No newline at end of file
diff --git a/.stats.yml b/.stats.yml
index 645b4c0b..cb4778c1 100644
--- a/.stats.yml
+++ b/.stats.yml
@@ -1,4 +1,4 @@
 configured_endpoints: 116
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/orb%2Forb-c2a4808c828c8288c5c8dfe2fdfa51d4d7c1bcc33cacc6b859d0cf4b35ce95cc.yml
-openapi_spec_hash: a2b5a1bfabbd03dd1b411791576eb502
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/orb%2Forb-d7b617958673f6e5b94781a63ed79caed27014e5ca8bbf7e5e31b8f4d135aecb.yml
+openapi_spec_hash: 66e9c2cd22385eed3ed507ee60aed4f5
 config_hash: 3c3524be9607afb24d2139ce26ce5389
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 01f2a1ea..f929bf3d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,18 @@
 # Changelog
 
+## 4.0.1 (2025-06-12)
+
+Full Changelog: [v4.0.0...v4.0.1](https://github.com/orbcorp/orb-python/compare/v4.0.0...v4.0.1)
+
+### Bug Fixes
+
+* **client:** correctly parse binary response | stream ([08ecc1c](https://github.com/orbcorp/orb-python/commit/08ecc1c10f8c26e66c02e333b89e910cedd61570))
+
+
+### Chores
+
+* **tests:** run tests in parallel ([f228f15](https://github.com/orbcorp/orb-python/commit/f228f15fa9f2fdaf5b7398a3f233aea4419ba3fb))
+
 ## 4.0.0 (2025-06-09)
 
 Full Changelog: [v3.24.0...v4.0.0](https://github.com/orbcorp/orb-python/compare/v3.24.0...v4.0.0)
diff --git a/pyproject.toml b/pyproject.toml
index 70da50d8..7315a5e0 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "orb-billing"
-version = "4.0.0"
+version = "4.0.1"
 description = "The official Python library for the orb API"
 dynamic = ["readme"]
 license = "Apache-2.0"
@@ -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/orbcorp/orb-python/tree/main/\g<2>)'
 
 [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 1596dacd..10dae689 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/orb/_base_client.py b/src/orb/_base_client.py
index 056620f0..79258719 100644
--- a/src/orb/_base_client.py
+++ b/src/orb/_base_client.py
@@ -1086,7 +1086,14 @@ def _process_response(
 
         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}")
 
@@ -1603,7 +1610,14 @@ async def _process_response(
 
         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/orb/_version.py b/src/orb/_version.py
index f6f2ef77..f7a7898e 100644
--- a/src/orb/_version.py
+++ b/src/orb/_version.py
@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "orb"
-__version__ = "4.0.0"  # x-release-please-version
+__version__ = "4.0.1"  # x-release-please-version