From 6e633d0bbf63849cb3f47e46cc65ed50cd5646e8 Mon Sep 17 00:00:00 2001
From: Wanis Elabbar <70503629+elabbarw@users.noreply.github.com>
Date: Thu, 6 Feb 2025 15:05:04 +0000
Subject: [PATCH] Fix pricing for Gemini 2.0 Flash 001

Model 	Type 	Price 	Price with Batch API
Gemini 2.0 Flash
1M Input tokens 	$0.15 	$0.075
1M Input audio tokens 	$1.00 	$0.50
1M Output text tokens 	$0.60 	$0.30

https://cloud.google.com/vertex-ai/generative-ai/pricing#token-based-pricing
---
 model_prices_and_context_window.json | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 71650cd42aae..fd949fb05512 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -3650,7 +3650,7 @@
         "supports_vision": true,
         "supports_response_schema": true,
         "supports_audio_output": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
         "supports_tool_choice": true
     },
     "gemini-2.0-flash-001": {
@@ -3663,9 +3663,9 @@
         "max_audio_length_hours": 8.4,
         "max_audio_per_prompt": 1,
         "max_pdf_size_mb": 30,
-        "input_cost_per_audio_token": 0.001,
-        "input_cost_per_token": 0.00015,
-        "output_cost_per_token": 0.0006,
+        "input_cost_per_audio_token": 0.000001,
+        "input_cost_per_token": 0.00000015,
+        "output_cost_per_token": 0.0000006,
         "litellm_provider": "vertex_ai-language-models",
         "mode": "chat",
         "supports_system_messages": true,
@@ -3674,7 +3674,7 @@
         "supports_response_schema": true,
         "supports_audio_output": true,
         "supports_tool_choice": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
     "gemini-2.0-flash-thinking-exp": {
         "max_tokens": 8192,