diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 926672b19a2..47cdfecfc0f 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -26063,6 +26063,7 @@
         "input_cost_per_token_batches": 1.5e-07,
         "input_cost_per_token_flex": 1.5e-07,
         "input_cost_per_token_priority": 5.4e-07,
+        "input_cost_per_audio_token_priority": 1.8e-06,
         "output_cost_per_token_batches": 1.25e-06,
         "output_cost_per_token_flex": 1.25e-06,
         "output_cost_per_token_priority": 4.5e-06,
@@ -26400,6 +26401,7 @@
         "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
+        "input_cost_per_audio_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
@@ -26595,6 +26597,7 @@
         "input_cost_per_token_batches": 5e-08,
         "input_cost_per_token_flex": 5e-08,
         "input_cost_per_token_priority": 1.8e-07,
+        "input_cost_per_audio_token_priority": 5.4e-07,
         "output_cost_per_token_batches": 2e-07,
         "output_cost_per_token_flex": 2e-07,
         "output_cost_per_token_priority": 7.2e-07,
@@ -49499,6 +49502,7 @@
         "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
+        "input_cost_per_audio_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 926672b19a2..47cdfecfc0f 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -26063,6 +26063,7 @@
         "input_cost_per_token_batches": 1.5e-07,
         "input_cost_per_token_flex": 1.5e-07,
         "input_cost_per_token_priority": 5.4e-07,
+        "input_cost_per_audio_token_priority": 1.8e-06,
         "output_cost_per_token_batches": 1.25e-06,
         "output_cost_per_token_flex": 1.25e-06,
         "output_cost_per_token_priority": 4.5e-06,
@@ -26400,6 +26401,7 @@
         "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
+        "input_cost_per_audio_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
@@ -26595,6 +26597,7 @@
         "input_cost_per_token_batches": 5e-08,
         "input_cost_per_token_flex": 5e-08,
         "input_cost_per_token_priority": 1.8e-07,
+        "input_cost_per_audio_token_priority": 5.4e-07,
         "output_cost_per_token_batches": 2e-07,
         "output_cost_per_token_flex": 2e-07,
         "output_cost_per_token_priority": 7.2e-07,
@@ -49499,6 +49502,7 @@
         "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
+        "input_cost_per_audio_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,