From cd0a1e600006b2f021f5ffd8f4220b467987d4ef Mon Sep 17 00:00:00 2001
From: Michael Clark <48897696+aoaim@users.noreply.github.com>
Date: Sun, 6 Apr 2025 00:20:01 +0800
Subject: [PATCH] Update model_prices (#9768)

---
 model_prices_and_context_window.json | 65 +++++++++++++++++++++++++++-
 1 file changed, 63 insertions(+), 2 deletions(-)

diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 8b88643f1a..e345815fb2 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -4847,6 +4847,33 @@
         "supports_tool_choice": true,
         "source": "https://ai.google.dev/pricing#2_0flash"
     },
+    "gemini/gemini-2.5-pro-preview-03-25": {
+        "max_tokens": 65536,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_images_per_prompt": 3000,
+        "max_videos_per_prompt": 10,
+        "max_video_length": 1,
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_pdf_size_mb": 30,
+        "input_cost_per_audio_token": 0.0000007,
+        "input_cost_per_token": 0.00000125,
+        "input_cost_per_token_above_128k_tokens": 0.0000025, 
+        "output_cost_per_token": 0.0000010,
+        "output_cost_per_token_above_128k_tokens": 0.000015, 
+        "litellm_provider": "gemini",
+        "mode": "chat",
+        "rpm": 10000,
+        "tpm": 10000000,
+        "supports_system_messages": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_response_schema": true,
+        "supports_audio_output": false,
+        "supports_tool_choice": true,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview"
+    },
     "gemini/gemini-2.0-flash-exp": {
         "max_tokens": 8192,
         "max_input_tokens": 1048576,
@@ -6665,6 +6692,14 @@
         "mode": "chat",
         "supports_tool_choice": true
     },
+    "mistralai/mistral-small-3.1-24b-instruct": {
+        "max_tokens": 32000,
+        "input_cost_per_token": 0.0000001,
+        "output_cost_per_token": 0.0000003,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
     "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": {
         "max_tokens": 32769,
         "input_cost_per_token": 0.0000005,
@@ -6793,12 +6828,38 @@
         "supports_vision": false,
         "supports_tool_choice": true
     },
+    "openrouter/openai/o3-mini": {
+        "max_tokens": 65536,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 65536,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false,
+        "supports_tool_choice": true
+    },
+    "openrouter/openai/o3-mini-high": {
+        "max_tokens": 65536,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 65536,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "litellm_provider": "openrouter",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_vision": false,
+        "supports_tool_choice": true
+    },
     "openrouter/openai/gpt-4o": {
         "max_tokens": 4096,
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "input_cost_per_token": 0.000005,
-        "output_cost_per_token": 0.000015,
+        "input_cost_per_token": 0.0000025,
+        "output_cost_per_token": 0.000010,
         "litellm_provider": "openrouter",
         "mode": "chat",
         "supports_function_calling": true,