From 21e27b13e6dd030bc4099ec82431705912d8a1fa Mon Sep 17 00:00:00 2001 From: o-khytrov Date: Fri, 25 Apr 2025 19:43:35 +0300 Subject: [PATCH] Update deprecation dates and prices (#10308) --- model_prices_and_context_window.json | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 760a7c7842..eb4b9f721e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -356,7 +356,8 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-07-14" }, "gpt-4o-audio-preview": { "max_tokens": 16384, @@ -1509,6 +1510,8 @@ }, "gpt-4o-transcribe": { "mode": "audio_transcription", + "max_input_tokens": 16000, + "max_output_tokens": 2000, "input_cost_per_token": 0.0000025, "input_cost_per_audio_token": 0.000006, "output_cost_per_token": 0.00001, @@ -1517,6 +1520,8 @@ }, "gpt-4o-mini-transcribe": { "mode": "audio_transcription", + "max_input_tokens": 16000, + "max_output_tokens": 2000, "input_cost_per_token": 0.00000125, "input_cost_per_audio_token": 0.000003, "output_cost_per_token": 0.000005, @@ -2439,7 +2444,8 @@ "supports_response_schema": true, "supports_vision": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-08-20" }, "azure/us/gpt-4o-2024-08-06": { "max_tokens": 16384, @@ -2479,13 +2485,15 @@ "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, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-12-20" }, "azure/global-standard/gpt-4o-mini": { "max_tokens": 16384, @@ -5349,14 +5357,14 @@ "input_cost_per_image": 0, "input_cost_per_video_per_second": 0, "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, + "input_cost_per_token": 0.00000015, "input_cost_per_character": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, + "output_cost_per_token": 0.0000006, "output_cost_per_character": 0, "output_cost_per_token_above_128k_tokens": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -5395,7 +5403,8 @@ "supports_tool_choice": true, "supported_modalities": ["text", "image", "audio", "video"], "supported_output_modalities": ["text", "image"], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "deprecation_date": "2026-02-05" }, "gemini-2.0-flash-thinking-exp": { "max_tokens": 8192, @@ -5599,7 +5608,8 @@ "supported_modalities": ["text", "image", "audio", "video"], "supported_output_modalities": ["text"], "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2026-02-25" }, "gemini-2.5-pro-preview-03-25": { "max_tokens": 65536,