Update model configs [2026-02-04T09:27:51.298Z]

Author: nikp1172

providers/azure-openai/azure-tts-hd.yaml

@@ -0,0 +1,6 @@
+model: azure-tts-hd
+costs:
+  input_cost_per_character: 0.00003
+mode: audio_speech
+defaultRegion: speech
+original_provider: azure

providers/azure-openai/azure-tts.yaml

@@ -0,0 +1,6 @@
+model: azure-tts
+costs:
+  input_cost_per_character: 0.000015
+mode: audio_speech
+defaultRegion: speech
+original_provider: azure

providers/azure-openai/gpt-4.1-2025-04-14.yaml

@@ -1,53 +1,15 @@
 model: gpt-4.1-2025-04-14
 costs:
-  input_cost_per_token: 0.000002
-  output_cost_per_token: 0.000008
-  input_cost_per_token_batches: 0.000001
-  output_cost_per_token_batches: 0.000004
-  cache_read_input_token_cost: 5.e-7
+  input_cost_per_token: 0.0000022
+  output_cost_per_token: 0.0000088
+  input_cost_per_token_batches: 0.0000011
+  output_cost_per_token_batches: 0.0000044
+  cache_read_input_token_cost: 5.5e-7
 limits:
-  max_tokens: 4096
+  max_tokens: 32768
   max_input_tokens: 1047576
   max_output_tokens: 32768
-features: [function_calling, parallel_function_calling, vision, chat, image]
-params:
-  - key: max_completion_tokens
-    defaultValue: 1000
-    minValue: 1
-    maxValue: 32768
-  - key: response_format
-    defaultValue: null
-    options:
-      - value: null
-        name: Text
-      - value: json_object
-        name: JSON Object
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_object
-      - value: json_schema
-        name: JSON Schema
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_schema
-            json_schema:
-              type: object
-        params:
-          key: json_schema
-          defaultValue: null
-          type: json
-          skipValues:
-            - null
-    skipValues:
-      - null
-    type: string
-removeParams:
-  - max_tokens
+features: [function_calling, parallel_function_calling, vision]
 mode: chat
+defaultRegion: us
 original_provider: azure

providers/azure-openai/gpt-4.1-mini-2025-04-14.yaml

@@ -1,53 +1,15 @@
 model: gpt-4.1-mini-2025-04-14
 costs:
-  input_cost_per_token: 4.e-7
-  output_cost_per_token: 0.0000016
-  input_cost_per_token_batches: 2.e-7
-  output_cost_per_token_batches: 8.e-7
-  cache_read_input_token_cost: 1.e-7
+  input_cost_per_token: 4.4e-7
+  output_cost_per_token: 0.00000176
+  input_cost_per_token_batches: 2.2e-7
+  output_cost_per_token_batches: 8.8e-7
+  cache_read_input_token_cost: 1.1e-7
 limits:
-  max_tokens: 4096
+  max_tokens: 32768
   max_input_tokens: 1047576
   max_output_tokens: 32768
-features: [function_calling, parallel_function_calling, vision, chat, image]
-params:
-  - key: max_completion_tokens
-    defaultValue: 1000
-    minValue: 1
-    maxValue: 32768
-  - key: response_format
-    defaultValue: null
-    options:
-      - value: null
-        name: Text
-      - value: json_object
-        name: JSON Object
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_object
-      - value: json_schema
-        name: JSON Schema
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_schema
-            json_schema:
-              type: object
-        params:
-          key: json_schema
-          defaultValue: null
-          type: json
-          skipValues:
-            - null
-    skipValues:
-      - null
-    type: string
-removeParams:
-  - max_tokens
+features: [function_calling, parallel_function_calling, vision]
 mode: chat
+defaultRegion: us
 original_provider: azure

providers/azure-openai/gpt-4.1-nano-2025-04-14.yaml

@@ -1,53 +1,15 @@
 model: gpt-4.1-nano-2025-04-14
 costs:
-  input_cost_per_token: 1.e-7
-  output_cost_per_token: 4.e-7
-  input_cost_per_token_batches: 5.e-8
-  output_cost_per_token_batches: 2.e-7
+  input_cost_per_token: 1.1e-7
+  output_cost_per_token: 4.4e-7
+  input_cost_per_token_batches: 6.e-8
+  output_cost_per_token_batches: 2.2e-7
   cache_read_input_token_cost: 2.5e-8
 limits:
-  max_tokens: 4096
+  max_tokens: 32768
   max_input_tokens: 1047576
   max_output_tokens: 32768
-features: [function_calling, parallel_function_calling, vision, chat, image]
-params:
-  - key: max_completion_tokens
-    defaultValue: 1000
-    minValue: 1
-    maxValue: 32768
-  - key: response_format
-    defaultValue: null
-    options:
-      - value: null
-        name: Text
-      - value: json_object
-        name: JSON Object
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_object
-      - value: json_schema
-        name: JSON Schema
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_schema
-            json_schema:
-              type: object
-        params:
-          key: json_schema
-          defaultValue: null
-          type: json
-          skipValues:
-            - null
-    skipValues:
-      - null
-    type: string
-removeParams:
-  - max_tokens
+features: [function_calling, parallel_function_calling, vision]
 mode: chat
+defaultRegion: us
 original_provider: azure

providers/azure-openai/gpt-4o-2024-08-06.yaml

@@ -1,54 +1,13 @@
 model: gpt-4o-2024-08-06
 costs:
-  input_cost_per_token: 0.0000025
-  output_cost_per_token: 0.00001
-  cache_read_input_token_cost: 0.00000125
+  input_cost_per_token: 0.00000275
+  output_cost_per_token: 0.000011
+  cache_read_input_token_cost: 0.000001375
 limits:
+  max_tokens: 16384
   max_input_tokens: 128000
   max_output_tokens: 16384
-features: [function_calling, parallel_function_calling, vision, chat, image]
-params:
-  - key: max_tokens
-    maxValue: 16384
-  - key: response_format
-    defaultValue: null
-    options:
-      - value: null
-        name: Text
-      - value: json_object
-        name: JSON Object
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_object
-      - value: json_schema
-        name: JSON Schema
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_schema
-            json_schema:
-              type: object
-        params:
-          key: json_schema
-          defaultValue: null
-          type: json
-          skipValues:
-            - null
-    skipValues:
-      - null
-    type: string
-  - key: frequency_penalty
-    defaultValue: 0
-    minValue: -2
-    maxValue: 2
-  - key: presence_penalty
-    defaultValue: 0
-    minValue: -2
-    maxValue: 2
+features: [function_calling, parallel_function_calling, vision]
 mode: chat
+defaultRegion: us
 original_provider: azure

providers/azure-openai/gpt-4o-2024-11-20.yaml

@@ -2,37 +2,12 @@ model: gpt-4o-2024-11-20
 costs:
   input_cost_per_token: 0.00000275
   output_cost_per_token: 0.000011
-  cache_read_input_token_cost: 0.00000125
+  cache_creation_input_token_cost: 0.00000138
 limits:
+  max_tokens: 16384
   max_input_tokens: 128000
   max_output_tokens: 16384
-features: [function_calling, parallel_function_calling, vision, chat, image]
-params:
-  - key: max_tokens
-    maxValue: 16384
-  - key: response_format
-    defaultValue: null
-    options:
-      - value: null
-        name: Text
-      - value: json_object
-        name: JSON Object
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_object
-    skipValues:
-      - null
-    type: string
-  - key: frequency_penalty
-    defaultValue: 0
-    minValue: -2
-    maxValue: 2
-  - key: presence_penalty
-    defaultValue: 0
-    minValue: -2
-    maxValue: 2
+features: [function_calling, parallel_function_calling, vision]
 mode: chat
+defaultRegion: us
 original_provider: azure

providers/azure-openai/gpt-4o-mini-2024-07-18.yaml

@@ -2,53 +2,12 @@ model: gpt-4o-mini-2024-07-18
 costs:
   input_cost_per_token: 1.65e-7
   output_cost_per_token: 6.6e-7
-  cache_read_input_token_cost: 7.5e-8
+  cache_read_input_token_cost: 8.3e-8
 limits:
+  max_tokens: 16384
   max_input_tokens: 128000
   max_output_tokens: 16384
-features: [function_calling, parallel_function_calling, vision, chat, image]
-params:
-  - key: max_tokens
-    maxValue: 16384
-  - key: response_format
-    defaultValue: null
-    options:
-      - value: null
-        name: Text
-      - value: json_object
-        name: JSON Object
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_object
-      - value: json_schema
-        name: JSON Schema
-        schema:
-          type: object
-          properties:
-            type:
-              type: string
-              value: json_schema
-            json_schema:
-              type: object
-        params:
-          key: json_schema
-          defaultValue: null
-          type: json
-          skipValues:
-            - null
-    skipValues:
-      - null
-    type: string
-  - key: frequency_penalty
-    defaultValue: 0
-    minValue: -2
-    maxValue: 2
-  - key: presence_penalty
-    defaultValue: 0
-    minValue: -2
-    maxValue: 2
+features: [function_calling, parallel_function_calling, vision]
 mode: chat
+defaultRegion: us
 original_provider: azure