diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py
index 36463a765d8..d8ed01bada5 100644
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@@ -1203,12 +1203,6 @@ class AmazonConverseConfig(BaseConfig):
         output_config: Optional[OutputConfigBlock] = inference_params.pop(
             "outputConfig", None
         )
-        # Strip routing prefixes (e.g. ``converse/``) and pass the provider
-        # explicitly so the declarative ``supports_output_config`` flag in
-        # ``model_prices_and_context_window.json`` is actually consulted.
-        # Passing ``custom_llm_provider=None`` would make ``_supports_factory``
-        # silently return False for any model whose name doesn't resolve to a
-        # known provider prefix on its own.
         if not _supports_factory(
             model=strip_bedrock_routing_prefix(model),
             custom_llm_provider="bedrock",
diff --git a/litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py b/litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py
index 6c7ff33b070..11e84f113c2 100644
--- a/litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py
+++ b/litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py
@@ -171,12 +171,6 @@ class AmazonAnthropicClaudeConfig(AmazonInvokeConfig, AnthropicConfig):
         anthropic_request.pop("model", None)
         anthropic_request.pop("stream", None)
         anthropic_request.pop("output_format", None)
-        # ``model`` reaches this transformation with an ``invoke/`` routing
-        # prefix (e.g. ``invoke/us.anthropic.claude-opus-4-6-v1``) which is
-        # not a valid provider and makes ``_supports_factory`` silently
-        # return False. Strip the routing prefix and pass the provider
-        # explicitly so the declarative ``supports_output_config`` flag in
-        # ``model_prices_and_context_window.json`` is actually consulted.
         if not _supports_factory(
             model=strip_bedrock_routing_prefix(model),
             custom_llm_provider="bedrock",
diff --git a/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py b/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py
index 9c74b2ffe0c..33e19a0a26f 100644
--- a/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py
+++ b/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py
@@ -510,11 +510,6 @@ class AmazonAnthropicClaudeMessagesConfig(
         # 5b. Bedrock Invoke supports output_config (effort) for Claude 4.6+ models,
         # but older models do not — strip it to avoid request rejection.
         # Ref: https://github.com/BerriAI/litellm/issues/22797
-        # ``model`` still carries the ``invoke/`` routing prefix here, which
-        # is not a valid provider and makes ``_supports_factory`` silently
-        # return False. Strip the prefix and pass the provider explicitly so
-        # the declarative ``supports_output_config`` flag in the cost map
-        # is actually consulted.
         if not _supports_factory(
             model=strip_bedrock_routing_prefix(model),
             custom_llm_provider="bedrock",