From 42eb356a44761a61dc38e91d5e64d71ce0da2023 Mon Sep 17 00:00:00 2001
From: Mohammad Mohtashim <45242107+keenborder786@users.noreply.github.com>
Date: Wed, 11 Jun 2025 01:00:00 +0500
Subject: [PATCH] [OpenAI]: Encoding Model (#31402)

- **Description:** Small Fix for when getting the encoder in case of
KeyError and using the correct encoder for newer models
- **Issue:** #31390
---
 libs/partners/openai/langchain_openai/chat_models/base.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/libs/partners/openai/langchain_openai/chat_models/base.py b/libs/partners/openai/langchain_openai/chat_models/base.py
index a1711cd6d7a..a9935e68dd1 100644
--- a/libs/partners/openai/langchain_openai/chat_models/base.py
+++ b/libs/partners/openai/langchain_openai/chat_models/base.py
@@ -1259,8 +1259,12 @@ class BaseChatOpenAI(BaseChatModel):
         try:
             encoding = tiktoken.encoding_for_model(model)
         except KeyError:
-            model = "cl100k_base"
-            encoding = tiktoken.get_encoding(model)
+            encoder = "cl100k_base"
+            if self.model_name.startswith("gpt-4o") or self.model_name.startswith(
+                "gpt-4.1"
+            ):
+                encoder = "o200k_base"
+            encoding = tiktoken.get_encoding(encoder)
         return model, encoding
 
     def get_token_ids(self, text: str) -> list[int]: