diff --git a/.env.example b/.env.example
index 1ad4b13a3c..8c49d88cc8 100644
--- a/.env.example
+++ b/.env.example
@@ -491,7 +491,6 @@ GEMINI_CLI_USER_AGENT="google-api-nodejs-client/10.3.0"
 # CLI_COMPAT_CLAUDE=1
 # CLI_COMPAT_GITHUB=1
 # CLI_COMPAT_ANTIGRAVITY=1
-# CLI_COMPAT_KIRO=1
 # CLI_COMPAT_CURSOR=1
 # CLI_COMPAT_KIMI_CODING=1
 # CLI_COMPAT_KILOCODE=1
@@ -509,20 +508,16 @@ GEMINI_CLI_USER_AGENT="google-api-nodejs-client/10.3.0"
 # Preferred setup: Dashboard → Providers → Add API Key.
 # Setting here is an alternative for Docker/headless deployments.
 
+# Static API keys for direct-authentication providers wired through the runtime.
+# OmniRoute loads provider credentials from the encrypted database or
+# data/provider-credentials.json. The variables below are documented escape
+# hatches that are referenced in code today.
 # DEEPSEEK_API_KEY=
-# GROQ_API_KEY=
-# XAI_API_KEY=
-# MISTRAL_API_KEY=
-# PERPLEXITY_API_KEY=
-# TOGETHER_API_KEY=
-# FIREWORKS_API_KEY=
-# CEREBRAS_API_KEY=
-# COHERE_API_KEY=
 # NVIDIA_API_KEY=
 
 # Embedding Providers (optional — used by /v1/embeddings)
-# NEBIUS_API_KEY=
-# Provider keys above (OpenAI, Mistral, Together, Fireworks, NVIDIA) also work for embeddings.
+# OpenAI/Mistral/Together/Fireworks/NVIDIA configured via Dashboard → Providers
+# also work for embeddings.
 
 
 # ═══════════════════════════════════════════════════════════════════════════════
@@ -783,9 +778,6 @@ APP_LOG_TO_FILE=true
 # ═══════════════════════════════════════════════════════════════════════════════
 # These variables enable verbose debugging output. NEVER enable in production.
 
-# Dump Cursor protobuf decode/encode details to console.
-# CURSOR_PROTOBUF_DEBUG=1
-
 # Dump raw Cursor SSE stream data to console.
 # CURSOR_STREAM_DEBUG=1