Fix PR review comments

litellm/llms/anthropic/cost_calculation.py

@@ -5,13 +5,52 @@ Helper util for handling anthropic-specific cost calculation
 
 from typing import TYPE_CHECKING, Optional, Tuple
 
-from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token
+from litellm.litellm_core_utils.llm_cost_calc.utils import (
+    _get_token_base_cost,
+    _parse_prompt_tokens_details,
+    calculate_cache_writing_cost,
+    generic_cost_per_token,
+)
 
 if TYPE_CHECKING:
     from litellm.types.utils import ModelInfo, Usage
 import litellm
 
 
+def _compute_cache_only_cost(model_info: "ModelInfo", usage: "Usage") -> float:
+    """
+    Return only the cache-related portion of the prompt cost (cache read + cache write).
+
+    These costs must NOT be scaled by geo/speed multipliers because the old
+    explicit ``fast/`` model entries carried unchanged cache rates while
+    multiplying only the regular input/output token costs.
+    """
+    if usage.prompt_tokens_details is None:
+        return 0.0
+
+    prompt_tokens_details = _parse_prompt_tokens_details(usage)
+    _, _, cache_creation_cost, cache_creation_cost_above_1hr, cache_read_cost = (
+        _get_token_base_cost(model_info=model_info, usage=usage)
+    )
+
+    cache_cost = float(prompt_tokens_details["cache_hit_tokens"]) * cache_read_cost
+
+    if (
+        prompt_tokens_details["cache_creation_tokens"]
+        or prompt_tokens_details["cache_creation_token_details"] is not None
+    ):
+        cache_cost += calculate_cache_writing_cost(
+            cache_creation_tokens=prompt_tokens_details["cache_creation_tokens"],
+            cache_creation_token_details=prompt_tokens_details[
+                "cache_creation_token_details"
+            ],
+            cache_creation_cost_above_1hr=cache_creation_cost_above_1hr,
+            cache_creation_cost=cache_creation_cost,
+        )
+
+    return cache_cost
+
+
 def cost_per_token(model: str, usage: "Usage") -> Tuple[float, float]:
     """
     Calculates the cost per token for a given model, prompt tokens, and completion tokens.
@@ -45,7 +84,8 @@ def cost_per_token(model: str, usage: "Usage") -> Tuple[float, float]:
             multiplier *= provider_specific_entry.get("fast", 1.0)
 
         if multiplier != 1.0:
-            prompt_cost *= multiplier
+            cache_cost = _compute_cache_only_cost(model_info=model_info, usage=usage)
+            prompt_cost = (prompt_cost - cache_cost) * multiplier + cache_cost
             completion_cost *= multiplier
     except Exception:
         pass

litellm/model_prices_and_context_window_backup.json

@@ -8489,7 +8489,7 @@
         "tool_use_system_prompt_tokens": 346,
         "provider_specific_entry": {
             "us": 1.1,
-            "fast": 1.1
+            "fast": 6.0
         }
     },
     "claude-opus-4-6-20260205": {
@@ -8524,7 +8524,7 @@
         "tool_use_system_prompt_tokens": 346,
         "provider_specific_entry": {
             "us": 1.1,
-            "fast": 1.1
+            "fast": 6.0
         }
     },
     "claude-sonnet-4-20250514": {

model_prices_and_context_window.json

@@ -8489,7 +8489,7 @@
         "tool_use_system_prompt_tokens": 346,
         "provider_specific_entry": {
             "us": 1.1,
-            "fast": 1.1
+            "fast": 6.0
         }
     },
     "claude-opus-4-6-20260205": {
@@ -8524,7 +8524,7 @@
         "tool_use_system_prompt_tokens": 346,
         "provider_specific_entry": {
             "us": 1.1,
-            "fast": 1.1
+            "fast": 6.0
         }
     },
     "claude-sonnet-4-20250514": {