From 9ec99cf9cec27ae5b8700ec5f0c0b5cf5495f1b2 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Mon, 10 Aug 2026 10:51:52 -0700 Subject: [PATCH] fix(model_prices): gpt-5-pro max output is 272k per OpenAI docs --- litellm/model_prices_and_context_window_backup.json | 8 ++++---- model_prices_and_context_window.json | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 873b1eb24d7..bfa506ee991 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -24778,8 +24778,8 @@ "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 272000, + "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, @@ -24815,8 +24815,8 @@ "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 272000, + "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 873b1eb24d7..bfa506ee991 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -24778,8 +24778,8 @@ "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 272000, + "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, @@ -24815,8 +24815,8 @@ "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 272000, + "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05,