Adjust model pricing metadata (#8147)

* added cache_read_input_token_cost * added input price for audio whisper * fixed prices for google gemini-1.0-pro-vision --------- Co-authored-by: yurii.izo <[email protected]>
BerriAI · Feb 1, 2025 · b844543 · b844543
1 parent ab939d8
commit b844543
Showing 1 changed file with 13 additions and 8 deletions.
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
@@ -915,7 +915,7 @@
     },
     "whisper-1": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0,
+        "input_cost_per_second": 0.0001,
         "output_cost_per_second": 0.0001, 
         "litellm_provider": "openai"
     }, 
@@ -941,7 +941,7 @@
     },
     "azure/whisper-1": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0, 
+        "input_cost_per_second": 0.0001, 
         "output_cost_per_second": 0.0001, 
         "litellm_provider": "azure"
     },
@@ -1047,6 +1047,7 @@
         "max_output_tokens": 16384,
         "input_cost_per_token": 0.00000275,
         "output_cost_per_token": 0.000011,
+        "cache_read_input_token_cost": 0.00000125,
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
@@ -1087,6 +1088,7 @@
         "max_output_tokens": 16384,
         "input_cost_per_token": 0.0000025,
         "output_cost_per_token": 0.000010,
+        "cache_read_input_token_cost": 0.00000125,
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
@@ -3334,8 +3336,9 @@
         "max_images_per_prompt": 16,
         "max_videos_per_prompt": 1,
         "max_video_length": 2,
-        "input_cost_per_token": 0.00000025, 
-        "output_cost_per_token": 0.0000005,
+        "input_cost_per_token": 0.0000005, 
+        "output_cost_per_token": 0.0000015,
+        "input_cost_per_image": 0.0025,
         "litellm_provider": "vertex_ai-vision-models",
         "mode": "chat",
         "supports_function_calling": true,
@@ -3349,8 +3352,9 @@
         "max_images_per_prompt": 16,
         "max_videos_per_prompt": 1,
         "max_video_length": 2,
-        "input_cost_per_token": 0.00000025, 
-        "output_cost_per_token": 0.0000005,
+        "input_cost_per_token": 0.0000005, 
+        "output_cost_per_token": 0.0000015,
+        "input_cost_per_image": 0.0025,
         "litellm_provider": "vertex_ai-vision-models",
         "mode": "chat",
         "supports_function_calling": true,
@@ -3364,8 +3368,9 @@
         "max_images_per_prompt": 16,
         "max_videos_per_prompt": 1,
         "max_video_length": 2,
-        "input_cost_per_token": 0.00000025, 
-        "output_cost_per_token": 0.0000005,
+        "input_cost_per_token": 0.0000005, 
+        "output_cost_per_token": 0.0000015,
+        "input_cost_per_image": 0.0025,
         "litellm_provider": "vertex_ai-vision-models",
         "mode": "chat",
         "supports_function_calling": true,