diff --git a/litellm/anthropic_beta_headers_config.json b/litellm/anthropic_beta_headers_config.json
index 7bb4c6e58df..b57239f8699 100644
--- a/litellm/anthropic_beta_headers_config.json
+++ b/litellm/anthropic_beta_headers_config.json
@@ -49,7 +49,7 @@
     "computer-use-2025-11-24": "computer-use-2025-11-24",
     "context-1m-2025-08-07": "context-1m-2025-08-07",
     "context-management-2025-06-27": "context-management-2025-06-27",
-    "dangerous-tool-use-2026-09-03": null,
+    "dangerous-tool-use-2026-09-03": "dangerous-tool-use-2026-09-03",
     "effort-2025-11-24": "effort-2025-11-24",
     "fast-mode-2026-02-01": null,
     "files-api-2025-04-14": "files-api-2025-04-14",
diff --git a/tests/unit/test_anthropic_beta_headers_filtering.py b/tests/unit/test_anthropic_beta_headers_filtering.py
index 8656a7564d2..1a6899f16ba 100644
--- a/tests/unit/test_anthropic_beta_headers_filtering.py
+++ b/tests/unit/test_anthropic_beta_headers_filtering.py
@@ -444,7 +444,7 @@ class TestAnthropicBetaHeadersFiltering:
 
         assert filtered == ["thinking-binding-controls-2026-08-01"]
 
-    @pytest.mark.parametrize("provider", ["anthropic", "bedrock", "bedrock_mantle", "vertex_ai"])
+    @pytest.mark.parametrize("provider", ["anthropic", "azure_ai", "bedrock", "bedrock_mantle", "vertex_ai"])
     def test_dangerous_tool_use_forwarded(self, provider):
         """Claude Code's server-side auto-mode classifier sends `safeguards` together with
         dangerous-tool-use-2026-09-03. Bedrock Invoke, Bedrock Mantle, and Vertex rawPredict