Add opt out varible for v1/messages to responses

litellm/__init__.py

@@ -197,6 +197,9 @@ telemetry = True
 max_tokens: int = DEFAULT_MAX_TOKENS  # OpenAI Defaults
 drop_params = bool(os.getenv("LITELLM_DROP_PARAMS", False))
 modify_params = bool(os.getenv("LITELLM_MODIFY_PARAMS", False))
+use_chat_completions_url_for_anthropic_messages: bool = bool(
+    os.getenv("LITELLM_USE_CHAT_COMPLETIONS_URL_FOR_ANTHROPIC_MESSAGES", False)
+)  # When True, routes OpenAI /v1/messages requests to chat/completions instead of the Responses API
 retry = True
 ### AUTH ###
 api_key: Optional[str] = None

litellm/llms/anthropic/experimental_pass_through/messages/handler.py

@@ -30,11 +30,17 @@ from .utils import AnthropicMessagesRequestUtils, mock_response
 
 # Providers that are routed directly to the OpenAI Responses API instead of
 # going through chat/completions.
-_RESPONSES_API_PROVIDERS = frozenset({"openai", "azure", "azure_text"})
+_RESPONSES_API_PROVIDERS = frozenset({"openai"})
 
 
 def _should_route_to_responses_api(custom_llm_provider: Optional[str]) -> bool:
-    """Return True when the provider should use the Responses API path."""
+    """Return True when the provider should use the Responses API path.
+
+    Set ``litellm.use_chat_completions_url_for_anthropic_messages = True`` to
+    opt out and route OpenAI/Azure requests through chat/completions instead.
+    """
+    if litellm.use_chat_completions_url_for_anthropic_messages:
+        return False
     return custom_llm_provider in _RESPONSES_API_PROVIDERS
 
 ####### ENVIRONMENT VARIABLES ###################