fix: add 1h cache pricing for vertex claude sonnet 4.6

litellm/litellm_core_utils/prompt_templates/factory.py

@@ -1393,10 +1393,10 @@ def convert_to_gemini_tool_call_invoke(
         if tool_calls is not None:
             for idx, tool in enumerate(tool_calls):
                 if "function" in tool:
-                    gemini_function_call: Optional[VertexFunctionCall] = (
-                        _gemini_tool_call_invoke_helper(
-                            function_call_params=tool["function"]
-                        )
+                    gemini_function_call: Optional[
+                        VertexFunctionCall
+                    ] = _gemini_tool_call_invoke_helper(
+                        function_call_params=tool["function"]
                     )
                     if gemini_function_call is not None:
                         part_dict: VertexPartType = {
@@ -1574,7 +1574,9 @@ def convert_to_gemini_tool_call_result(  # noqa: PLR0915
                         file_data = (
                             file_content.get("file_data", "")
                             if isinstance(file_content, dict)
-                            else file_content if isinstance(file_content, str) else ""
+                            else file_content
+                            if isinstance(file_content, str)
+                            else ""
                         )
 
                     if file_data:
@@ -2079,9 +2081,9 @@ def _sanitize_empty_text_content(
         if isinstance(content, str):
             if not content or not content.strip():
                 message = cast(AllMessageValues, dict(message))  # Make a copy
-                message["content"] = (
-                    "[System: Empty message content sanitised to satisfy protocol]"
-                )
+                message[
+                    "content"
+                ] = "[System: Empty message content sanitised to satisfy protocol]"
                 verbose_logger.debug(
                     f"_sanitize_empty_text_content: Replaced empty text content in {message.get('role')} message"
                 )
@@ -2421,9 +2423,9 @@ def anthropic_messages_pt(  # noqa: PLR0915
                             # Convert ChatCompletionImageUrlObject to dict if needed
                             image_url_value = m["image_url"]
                             if isinstance(image_url_value, str):
-                                image_url_input: Union[str, dict[str, Any]] = (
-                                    image_url_value
-                                )
+                                image_url_input: Union[
+                                    str, dict[str, Any]
+                                ] = image_url_value
                             else:
                                 # ChatCompletionImageUrlObject or dict case - convert to dict
                                 image_url_input = {
@@ -2450,9 +2452,9 @@ def anthropic_messages_pt(  # noqa: PLR0915
                             )
 
                             if "cache_control" in _content_element:
-                                _anthropic_content_element["cache_control"] = (
-                                    _content_element["cache_control"]
-                                )
+                                _anthropic_content_element[
+                                    "cache_control"
+                                ] = _content_element["cache_control"]
                             user_content.append(_anthropic_content_element)
                         elif m.get("type", "") == "text":
                             m = cast(ChatCompletionTextObject, m)
@@ -2512,9 +2514,9 @@ def anthropic_messages_pt(  # noqa: PLR0915
                     )
 
                     if "cache_control" in _content_element:
-                        _anthropic_content_text_element["cache_control"] = (
-                            _content_element["cache_control"]
-                        )
+                        _anthropic_content_text_element[
+                            "cache_control"
+                        ] = _content_element["cache_control"]
 
                     user_content.append(_anthropic_content_text_element)
 
@@ -2647,9 +2649,9 @@ def anthropic_messages_pt(  # noqa: PLR0915
                         original_content_element=dict(assistant_content_block),
                     )
                     if "cache_control" in _content_element:
-                        _anthropic_text_content_element["cache_control"] = (
-                            _content_element["cache_control"]
-                        )
+                        _anthropic_text_content_element[
+                            "cache_control"
+                        ] = _content_element["cache_control"]
                     text_element = _anthropic_text_content_element
 
                 # Interleave: each thinking block precedes its server tool group.
@@ -2809,9 +2811,9 @@ def anthropic_messages_pt(  # noqa: PLR0915
                     )
 
                     if "cache_control" in _content_element:
-                        _anthropic_text_content_element["cache_control"] = (
-                            _content_element["cache_control"]
-                        )
+                        _anthropic_text_content_element[
+                            "cache_control"
+                        ] = _content_element["cache_control"]
 
                     assistant_content.append(_anthropic_text_content_element)
 
@@ -5291,7 +5293,9 @@ def default_response_schema_prompt(response_schema: dict) -> str:
     prompt_str = """Use this JSON schema: 
     ```json 
     {}
-    ```""".format(response_schema)
+    ```""".format(
+        response_schema
+    )
     return prompt_str
 
 

litellm/model_prices_and_context_window_backup.json

@@ -31472,6 +31472,7 @@
     },
     "vertex_ai/claude-sonnet-4-6": {
         "cache_creation_input_token_cost": 3.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
@@ -38339,6 +38340,7 @@
     },
     "vertex_ai/claude-sonnet-4-6@default": {
         "cache_creation_input_token_cost": 3.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "vertex_ai-anthropic_models",

model_prices_and_context_window.json

@@ -31508,6 +31508,7 @@
     },
     "vertex_ai/claude-sonnet-4-6": {
         "cache_creation_input_token_cost": 3.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
@@ -38402,6 +38403,7 @@
     },
     "vertex_ai/claude-sonnet-4-6@default": {
         "cache_creation_input_token_cost": 3.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "vertex_ai-anthropic_models",

tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py

@@ -698,6 +698,34 @@ def test_cache_writing_cost_with_zero_creation_tokens_and_ephemeral_details():
     assert round(result, 6) == round(expected, 6)
 
 
+def test_vertex_ai_claude_sonnet_4_6_1h_cache_writes_are_priced():
+    os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+
+    usage = Usage(
+        prompt_tokens=0,
+        completion_tokens=0,
+        total_tokens=0,
+        prompt_tokens_details=PromptTokensDetailsWrapper(
+            cached_tokens=0,
+            cache_creation_tokens=0,
+            cache_creation_token_details=CacheCreationTokenDetails(
+                ephemeral_5m_input_tokens=0,
+                ephemeral_1h_input_tokens=1_000_000,
+            ),
+        ),
+    )
+
+    prompt_cost, completion_cost = generic_cost_per_token(
+        model="claude-sonnet-4-6",
+        usage=usage,
+        custom_llm_provider="vertex_ai",
+    )
+
+    assert prompt_cost == 6.0
+    assert completion_cost == 0.0
+
+
 def test_service_tier_flex_pricing():
     """Test that flex service tier uses correct pricing (approximately 50% of standard)."""
     # Set up environment for local model cost map

tests/test_litellm/test_claude_opus_4_6_config.py

@@ -226,6 +226,22 @@ def test_opus_4_6_alias_and_dated_metadata_match():
         assert alias[key] == dated[key], f"Mismatch for {key}"
 
 
+def test_vertex_ai_claude_sonnet_4_6_has_1h_cache_write_pricing_in_root_map():
+    json_path = os.path.join(
+        os.path.dirname(__file__), "../../model_prices_and_context_window.json"
+    )
+    with open(json_path) as f:
+        model_data = json.load(f)
+
+    vertex_entries = [
+        "vertex_ai/claude-sonnet-4-6",
+        "vertex_ai/claude-sonnet-4-6@default",
+    ]
+
+    for model_name in vertex_entries:
+        assert model_data[model_name]["cache_creation_input_token_cost_above_1hr"] == 6e-06
+
+
 def test_opus_4_6_bedrock_converse_registration():
     assert "anthropic.claude-opus-4-6-v1" in litellm.BEDROCK_CONVERSE_MODELS
     assert "global.anthropic.claude-opus-4-6-v1" in litellm.bedrock_converse_models