From 15462f7d1d46981bcdae318909acbc9d587b8603 Mon Sep 17 00:00:00 2001
From: xbrxr03 <abrarhabib03@gmail.com>
Date: Sun, 21 Jun 2026 20:09:45 -0400
Subject: [PATCH] fix: correct context window tokens for GPT-5 Pro and GPT-5.4
 Mini/Nano
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Three bugs in model_prices_and_context_window.json:

1. gpt-5-pro and gpt-5-pro-2025-10-06: max_input_tokens and max_tokens
   were SWAPPED. GPT-5 Pro has a 400K context window (input) with 128K
   max output, but the values were set as max_input=128000,
   max_tokens=272000. This caused token limit errors when sending
   prompts over 128K tokens to GPT-5 Pro.

2. gpt-5.4-mini and gpt-5.4-mini-2026-03-17: max_input_tokens was
   272000, but GPT-5.4 Mini shares the same 1,050,000 token context
   window as GPT-5.4. This was inconsistent with the azure/ variants
   which already correctly had 1,050,000.

3. gpt-5.4-nano and gpt-5.4-nano-2026-03-17: same issue as Mini,
   max_input_tokens was 272000 instead of 1,050,000.

Source: OpenAI model documentation and contextwindows.dev which
aggregates official context window sizes.

Fixes #30928 (partially — the issue incorrectly claims gpt-5/gpt-5-mini
should be 400K; their 272K values are correct per OpenAI docs)
---
 model_prices_and_context_window.json | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 3e844a8e3ed..77e968fb864 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -22388,7 +22388,7 @@
         "input_cost_per_token_batches": 3.75e-07,
         "input_cost_per_token_priority": 1.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -22436,7 +22436,7 @@
         "input_cost_per_token_batches": 3.75e-07,
         "input_cost_per_token_priority": 1.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -22482,7 +22482,7 @@
         "input_cost_per_token_flex": 1e-07,
         "input_cost_per_token_batches": 1e-07,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -22527,7 +22527,7 @@
         "input_cost_per_token_flex": 1e-07,
         "input_cost_per_token_batches": 1e-07,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -22568,9 +22568,9 @@
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 272000,
-        "max_tokens": 272000,
+        "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,
@@ -22604,9 +22604,9 @@
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 272000,
-        "max_tokens": 272000,
+        "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,