Restore cache_creation_tokens breakdown in UsageMetrics normalization.

Keep cache writes as a separate breakdown field while they remain folded into prompt_tokens for billed totals.

docs/edge/en/concepts/flows.mdx

@@ -277,10 +277,13 @@ The returned [`UsageMetrics`](https://github.com/crewAIInc/crewAI/blob/main/lib/
 | `prompt_tokens` | Full input/prompt tokens billed for the request |
 | `completion_tokens` | Output/completion tokens billed for the request |
 | `cached_prompt_tokens` | Cache-read subset of prompt tokens (breakdown only) |
+| `cache_creation_tokens` | Cache-write subset of prompt tokens (breakdown only, Anthropic) |
 | `reasoning_tokens` | Reasoning/thinking subset where the provider reports it separately (breakdown only) |
 | `successful_requests` | Number of LLM calls aggregated |
 
-Breakdown fields such as `cached_prompt_tokens` and `reasoning_tokens` are **not** added on top of `total_tokens` — they describe portions already included in `prompt_tokens` or `completion_tokens`.
+Breakdown fields such as `cached_prompt_tokens`, `cache_creation_tokens`, and
+`reasoning_tokens` are **not** added on top of `total_tokens` — they describe
+portions already included in `prompt_tokens` or `completion_tokens`.
 
 For Anthropic, cache read and cache write counters are folded into `prompt_tokens`, so cached workloads are fully reflected in `total_tokens`. OpenAI-style providers already include cached input inside `prompt_tokens`; CrewAI surfaces the cached portion separately for visibility.
 

docs/edge/en/concepts/llms.mdx

@@ -427,7 +427,7 @@ In this section, you'll find detailed examples that help you select, configure,
 
     `cached_prompt_tokens` records the cache-read portion as a breakdown only; it is
     already included in `prompt_tokens` and must not be added again to
-    `total_tokens`.
+    `total_tokens`. `cache_creation_tokens` records cache writes the same way.
 
     ```python Code
     usage = llm.get_token_usage_summary()

lib/crewai/src/crewai/types/usage_metrics.py

@@ -177,11 +177,16 @@ class UsageMetrics(BaseModel):
             if isinstance(details, dict):
                 cached_prompt_tokens = _coerce_int(details.get("cached_tokens"))
 
+        cache_creation_tokens = _coerce_int(
+            usage_data.get("cache_creation_tokens")
+        ) or _coerce_int(usage_data.get("cache_creation_input_tokens"))
+
         return cls(
             total_tokens=prompt_tokens + completion_tokens,
             prompt_tokens=prompt_tokens,
             completion_tokens=completion_tokens,
             cached_prompt_tokens=cached_prompt_tokens,
             reasoning_tokens=_coerce_int(usage_data.get("reasoning_tokens")),
+            cache_creation_tokens=cache_creation_tokens,
             successful_requests=1,
         )

lib/crewai/tests/events/test_llm_usage_event.py

@@ -331,6 +331,7 @@ class TestFromProviderDictAnthropicCacheTokens:
         assert metrics is not None
         assert metrics.prompt_tokens == 120
         assert metrics.total_tokens == 170
+        assert metrics.cache_creation_tokens == 20
 
     def test_cache_read_and_creation_tokens_both_included(self):
         from crewai.types.usage_metrics import UsageMetrics
@@ -348,6 +349,7 @@ class TestFromProviderDictAnthropicCacheTokens:
         assert metrics.prompt_tokens == 150
         assert metrics.total_tokens == 200
         assert metrics.cached_prompt_tokens == 30
+        assert metrics.cache_creation_tokens == 20
 
     def test_missing_cache_fields_preserve_non_cached_totals(self):
         from crewai.types.usage_metrics import UsageMetrics
@@ -360,6 +362,7 @@ class TestFromProviderDictAnthropicCacheTokens:
         assert metrics.prompt_tokens == 100
         assert metrics.total_tokens == 150
         assert metrics.cached_prompt_tokens == 0
+        assert metrics.cache_creation_tokens == 0
 
     def test_reconciled_native_dict_is_not_double_counted(self):
         from crewai.types.usage_metrics import UsageMetrics
@@ -369,12 +372,14 @@ class TestFromProviderDictAnthropicCacheTokens:
                 "input_tokens": 150,
                 "output_tokens": 50,
                 "cached_prompt_tokens": 30,
+                "cache_creation_tokens": 20,
             }
         )
 
         assert metrics is not None
         assert metrics.prompt_tokens == 150
         assert metrics.total_tokens == 200
+        assert metrics.cache_creation_tokens == 20
 
     def test_openai_cached_prompt_tokens_are_not_added_twice(self):
         from crewai.types.usage_metrics import UsageMetrics

lib/crewai/tests/test_flow_usage_metrics.py

@@ -130,6 +130,7 @@ class TestUsageDictToMetrics:
                     "total_tokens": 180,
                     "cached_prompt_tokens": 40,
                     "reasoning_tokens": 25,
+                    "cache_creation_tokens": 10,
                 },
                 UsageMetrics(
                     prompt_tokens=100,
@@ -137,6 +138,7 @@ class TestUsageDictToMetrics:
                     total_tokens=180,
                     cached_prompt_tokens=40,
                     reasoning_tokens=25,
+                    cache_creation_tokens=10,
                     successful_requests=1,
                 ),
             ),