feat(google-vertex): update model YAMLs [bot]

providers/google-vertex/anthropic/claude-haiku-4-5.yaml

@@ -1,26 +1,30 @@
 costs:
     - cache_creation_input_token_cost: 0.000001375
+      cache_creation_input_token_cost_per_hour: 0.0000022
       cache_read_input_token_cost: 1.1e-7
       input_cost_per_token: 0.0000011
       input_cost_per_token_batches: 5.5e-7
       output_cost_per_token: 0.0000055
       output_cost_per_token_batches: 0.00000275
       region: us-east5
     - cache_creation_input_token_cost: 0.00000125
+      cache_creation_input_token_cost_per_hour: 0.000002
       cache_read_input_token_cost: 1e-7
       input_cost_per_token: 0.000001
       input_cost_per_token_batches: 5e-7
       output_cost_per_token: 0.000005
       output_cost_per_token_batches: 0.0000025
       region: global
     - cache_creation_input_token_cost: 0.000001375
+      cache_creation_input_token_cost_per_hour: 0.0000022
       cache_read_input_token_cost: 1.1e-7
       input_cost_per_token: 0.0000011
       input_cost_per_token_batches: 5.5e-7
       output_cost_per_token: 0.0000055
       output_cost_per_token_batches: 0.00000275
       region: europe-west1
     - cache_creation_input_token_cost: 0.000001375
+      cache_creation_input_token_cost_per_hour: 0.0000022
       cache_read_input_token_cost: 1.1e-7
       input_cost_per_token: 0.0000011
       input_cost_per_token_batches: 5.5e-7

providers/google-vertex/anthropic/claude-haiku-4-5@20251001.yaml

@@ -1,26 +1,30 @@
 costs:
     - cache_creation_input_token_cost: 0.000001375
+      cache_creation_input_token_cost_per_hour: 0.0000022
       cache_read_input_token_cost: 1.1e-7
       input_cost_per_token: 0.0000011
       input_cost_per_token_batches: 5.5e-7
       output_cost_per_token: 0.0000055
       output_cost_per_token_batches: 0.00000275
       region: us-east5
     - cache_creation_input_token_cost: 0.00000125
+      cache_creation_input_token_cost_per_hour: 0.000002
       cache_read_input_token_cost: 1e-7
       input_cost_per_token: 0.000001
       input_cost_per_token_batches: 5e-7
       output_cost_per_token: 0.000005
       output_cost_per_token_batches: 0.0000025
       region: global
     - cache_creation_input_token_cost: 0.000001375
+      cache_creation_input_token_cost_per_hour: 0.0000022
       cache_read_input_token_cost: 1.1e-7
       input_cost_per_token: 0.0000011
       input_cost_per_token_batches: 5.5e-7
       output_cost_per_token: 0.0000055
       output_cost_per_token_batches: 0.00000275
       region: europe-west1
     - cache_creation_input_token_cost: 0.000001375
+      cache_creation_input_token_cost_per_hour: 0.0000022
       cache_read_input_token_cost: 1.1e-7
       input_cost_per_token: 0.0000011
       input_cost_per_token_batches: 5.5e-7
@@ -53,6 +57,7 @@ params:
 provisioning: serverless
 sources:
     - https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5
+    - https://platform.claude.com/docs/en/about-claude/pricing
 status: active
 supportedModes:
     - chat

providers/google-vertex/anthropic/claude-opus-4-1.yaml

@@ -1,12 +1,14 @@
 costs:
     - cache_creation_input_token_cost: 0.00001875
+      cache_creation_input_token_cost_per_hour: 0.00003
       cache_read_input_token_cost: 0.0000015
       input_cost_per_token: 0.000015
       input_cost_per_token_batches: 0.0000075
       output_cost_per_token: 0.000075
       output_cost_per_token_batches: 0.0000375
       region: us-east5
     - cache_creation_input_token_cost: 0.00001875
+      cache_creation_input_token_cost_per_hour: 0.00003
       cache_read_input_token_cost: 0.0000015
       input_cost_per_token: 0.000015
       input_cost_per_token_batches: 0.0000075
@@ -15,9 +17,12 @@ costs:
       region: global
 features:
     - function_calling
+    - parallel_function_calling
     - tool_choice
     - assistant_prefill
     - prompt_caching
+    - cache_control
+    - system_messages
 limits:
     context_window: 200000
     max_input_tokens: 200000

providers/google-vertex/anthropic/claude-opus-4-1@20250805.yaml

@@ -1,18 +1,21 @@
 costs:
     - cache_creation_input_token_cost: 0.00001875
+      cache_creation_input_token_cost_per_hour: 0.00003
       cache_read_input_token_cost: 0.0000015
       input_cost_per_token: 0.000015
       input_cost_per_token_batches: 0.0000075
       output_cost_per_token: 0.000075
       output_cost_per_token_batches: 0.0000375
       region: us-east5
     - cache_creation_input_token_cost: 0.00001875
+      cache_creation_input_token_cost_per_hour: 0.00003
       cache_read_input_token_cost: 0.0000015
       input_cost_per_token: 0.000015
       input_cost_per_token_batches: 0.0000075
       output_cost_per_token: 0.000075
       output_cost_per_token_batches: 0.0000375
       region: global
+deprecationDate: "2026-08-05"
 features:
     - function_calling
     - tool_choice

providers/google-vertex/anthropic/claude-opus-4-5.yaml

@@ -1,26 +1,30 @@
 costs:
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       input_cost_per_token_batches: 0.00000275
       output_cost_per_token: 0.0000275
       output_cost_per_token_batches: 0.00001375
       region: us-east5
     - cache_creation_input_token_cost: 0.00000625
+      cache_creation_input_token_cost_per_hour: 0.00001
       cache_read_input_token_cost: 5e-7
       input_cost_per_token: 0.000005
       input_cost_per_token_batches: 0.0000025
       output_cost_per_token: 0.000025
       output_cost_per_token_batches: 0.0000125
       region: global
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       input_cost_per_token_batches: 0.00000275
       output_cost_per_token: 0.0000275
       output_cost_per_token_batches: 0.00001375
       region: europe-west1
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       input_cost_per_token_batches: 0.00000275

providers/google-vertex/anthropic/claude-opus-4-5@20251101.yaml

@@ -1,20 +1,24 @@
 costs:
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       output_cost_per_token: 0.0000275
       region: us-east5
     - cache_creation_input_token_cost: 0.00000625
+      cache_creation_input_token_cost_per_hour: 0.00001
       cache_read_input_token_cost: 5e-7
       input_cost_per_token: 0.000005
       output_cost_per_token: 0.000025
       region: global
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       output_cost_per_token: 0.0000275
       region: europe-west1
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       output_cost_per_token: 0.0000275
@@ -52,6 +56,7 @@ sources:
     - https://platform.claude.com/docs/en/about-claude/models/overview
     - https://platform.claude.com/docs/en/about-claude/pricing
     - https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai
+    - https://platform.claude.com/docs/en/about-claude/model-deprecations
 status: active
 supportedModes:
     - chat

providers/google-vertex/anthropic/claude-opus-4-6.yaml

@@ -1,22 +1,26 @@
 costs:
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       output_cost_per_token: 0.0000275
       region: us-east5
     - cache_creation_input_token_cost: 0.00000625
+      cache_creation_input_token_cost_per_hour: 0.00001
       cache_read_input_token_cost: 5e-7
       input_cost_per_token: 0.000005
       input_cost_per_token_batches: 0.0000025
       output_cost_per_token: 0.000025
       output_cost_per_token_batches: 0.0000125
       region: global
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       output_cost_per_token: 0.0000275
       region: europe-west1
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       output_cost_per_token: 0.0000275

providers/google-vertex/anthropic/claude-opus-4-6@default.yaml

@@ -1,26 +1,30 @@
 costs:
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       input_cost_per_token_batches: 0.00000275
       output_cost_per_token: 0.0000275
       output_cost_per_token_batches: 0.00001375
       region: us-east5
     - cache_creation_input_token_cost: 0.00000625
+      cache_creation_input_token_cost_per_hour: 0.00001
       cache_read_input_token_cost: 5e-7
       input_cost_per_token: 0.000005
       input_cost_per_token_batches: 0.0000025
       output_cost_per_token: 0.000025
       output_cost_per_token_batches: 0.0000125
       region: global
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       input_cost_per_token_batches: 0.00000275
       output_cost_per_token: 0.0000275
       output_cost_per_token_batches: 0.00001375
       region: europe-west1
     - cache_creation_input_token_cost: 0.000006875
+      cache_creation_input_token_cost_per_hour: 0.000011
       cache_read_input_token_cost: 5.5e-7
       input_cost_per_token: 0.0000055
       input_cost_per_token_batches: 0.00000275

providers/google-vertex/anthropic/claude-opus-4.yaml

@@ -1,12 +1,14 @@
 costs:
     - cache_creation_input_token_cost: 0.00001875
+      cache_creation_input_token_cost_per_hour: 0.00003
       cache_read_input_token_cost: 0.0000015
       input_cost_per_token: 0.000015
       input_cost_per_token_batches: 0.0000075
       output_cost_per_token: 0.000075
       output_cost_per_token_batches: 0.0000375
       region: us-east5
     - cache_creation_input_token_cost: 0.00001875
+      cache_creation_input_token_cost_per_hour: 0.00003
       cache_read_input_token_cost: 0.0000015
       input_cost_per_token: 0.000015
       input_cost_per_token_batches: 0.0000075
@@ -18,6 +20,7 @@ features:
     - tool_choice
     - prompt_caching
     - assistant_prefill
+    - system_messages
 limits:
     context_window: 200000
     max_input_tokens: 200000
@@ -42,8 +45,8 @@ provisioning: serverless
 sources:
     - https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/opus-4
     - https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude
-    - https://platform.claude.com/docs/en/docs/about-claude/models
     - https://platform.claude.com/docs/en/about-claude/pricing
+    - https://platform.claude.com/docs/en/about-claude/model-deprecations
 status: active
 supportedModes:
     - chat

providers/google-vertex/anthropic/claude-sonnet-4-5.yaml

@@ -1,5 +1,6 @@
 costs:
     - cache_creation_input_token_cost: 0.000004125
+      cache_creation_input_token_cost_per_hour: 0.0000066
       cache_read_input_token_cost: 3.3e-7
       input_cost_per_token: 0.0000033
       output_cost_per_token: 0.0000165
@@ -18,7 +19,28 @@ costs:
               - cost_per_token: 0.00002475
                 from: 200000
           pricing_mode: marginal
+    - cache_creation_input_token_cost: 0.000004125
+      cache_creation_input_token_cost_per_hour: 0.0000066
+      cache_read_input_token_cost: 3.3e-7
+      input_cost_per_token: 0.0000033
+      output_cost_per_token: 0.0000165
+      region: us
+      tiered_pricing:
+          cache_read:
+              - cost_per_token: 6.6e-7
+                from: 200000
+          cache_write:
+              - cost_per_token: 0.00000825
+                from: 200000
+          input:
+              - cost_per_token: 0.0000066
+                from: 200000
+          output:
+              - cost_per_token: 0.00002475
+                from: 200000
+          pricing_mode: marginal
     - cache_creation_input_token_cost: 0.00000375
+      cache_creation_input_token_cost_per_hour: 0.000006
       cache_read_input_token_cost: 3e-7
       input_cost_per_token: 0.000003
       input_cost_per_token_batches: 0.0000015
@@ -40,6 +62,7 @@ costs:
                 from: 200000
           pricing_mode: marginal
     - cache_creation_input_token_cost: 0.000004125
+      cache_creation_input_token_cost_per_hour: 0.0000066
       cache_read_input_token_cost: 3.3e-7
       input_cost_per_token: 0.0000033
       output_cost_per_token: 0.0000165
@@ -59,6 +82,27 @@ costs:
                 from: 200000
           pricing_mode: marginal
     - cache_creation_input_token_cost: 0.000004125
+      cache_creation_input_token_cost_per_hour: 0.0000066
+      cache_read_input_token_cost: 3.3e-7
+      input_cost_per_token: 0.0000033
+      output_cost_per_token: 0.0000165
+      region: eu
+      tiered_pricing:
+          cache_read:
+              - cost_per_token: 6.6e-7
+                from: 200000
+          cache_write:
+              - cost_per_token: 0.00000825
+                from: 200000
+          input:
+              - cost_per_token: 0.0000066
+                from: 200000
+          output:
+              - cost_per_token: 0.00002475
+                from: 200000
+          pricing_mode: marginal
+    - cache_creation_input_token_cost: 0.000004125
+      cache_creation_input_token_cost_per_hour: 0.0000066
       cache_read_input_token_cost: 3.3e-7
       input_cost_per_token: 0.0000033
       output_cost_per_token: 0.0000165