From d9664a3ee49e0c5f7ee3f5bb552a349994daa708 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Wed, 1 Oct 2025 14:35:57 -0700 Subject: [PATCH] fix gpt-5-chat-latest on model cost map (#15116) --- litellm/model_prices_and_context_window_backup.json | 12 ++++++------ model_prices_and_context_window.json | 12 ++++++------ 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 877df1bb78..1d12d1a74a 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2004,9 +2004,9 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -12830,9 +12830,9 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 877df1bb78..1d12d1a74a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -2004,9 +2004,9 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -12830,9 +12830,9 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [