From 4e3cb7ac71fa4f5a98f6e806b5d1f0e7fc78285b Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Sat, 11 Jul 2026 11:18:56 +0000
Subject: [PATCH] chore: drop env-var default for pin_deployment_credentials
 (avoid undocumented env key)

---
 litellm/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/litellm/__init__.py b/litellm/__init__.py
index c5b6087a029..f4ff4cde5de 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -240,7 +240,7 @@ use_chat_completions_url_for_anthropic_messages: bool = bool(
 # Or via `litellm_settings.strip_anthropic_total_tokens: true` in
 # config.yaml.
 strip_anthropic_total_tokens: bool = False
-pin_deployment_credentials: bool = bool(os.getenv("LITELLM_PIN_DEPLOYMENT_CREDENTIALS", False))
+pin_deployment_credentials: bool = False
 route_all_chat_openai_to_responses: bool = (
     os.getenv("LITELLM_ROUTE_ALL_CHAT_OPENAI_TO_RESPONSES", "false").lower() == "true"
 )  # When True, routes all OpenAI /chat/completions requests through the Responses API bridge