diff --git a/README.md b/README.md
index f52f481c0..f46e40640 100644
--- a/README.md
+++ b/README.md
@@ -227,7 +227,7 @@ shows an **Output Tokens Saved** card next to input compression, labelled
 |--------------|:---------------:|----------------------------------|
 | Claude Code  | ✅              | `--memory` · `--code-graph` · `--1m` · `--tool-search` |
 | Codex        | ✅              | shares memory with Claude        |
-| Grok CLI     | ✅              | routes via `GROK_CLI_CHAT_PROXY_BASE_URL` |
+| Grok CLI     | ✅              | routes via `GROK_MODELS_BASE_URL` |
 | Cursor       | Manual setup    | starts proxy and prints base URLs for Cursor settings |
 | Aider        | ✅              | starts proxy + launches          |
 | Copilot CLI  | ✅              | starts proxy + launches          |
diff --git a/headroom/cli/wrap.py b/headroom/cli/wrap.py
index 29b706744..5c5f37a79 100644
--- a/headroom/cli/wrap.py
+++ b/headroom/cli/wrap.py
@@ -6381,9 +6381,10 @@ def grok(
     """Launch Grok CLI through Headroom proxy.
 
     \b
-    Sets ``GROK_CLI_CHAT_PROXY_BASE_URL`` so Grok routes inference traffic
-    through Headroom. Registers the headroom MCP server in ``~/.grok/config.toml``
-    so Grok can call ``headroom_retrieve`` on compression markers.
+    Sets ``GROK_MODELS_BASE_URL`` so Grok routes inference traffic through
+    Headroom while preserving native settings and authentication routing.
+    Registers the headroom MCP server in ``~/.grok/config.toml`` so Grok can
+    call ``headroom_retrieve`` on compression markers.
 
     \b
     Examples:
@@ -8210,10 +8211,11 @@ def unwrap_omp(port: int, no_stop_proxy: bool) -> None:
 def unwrap_grok(port: int, no_stop_proxy: bool) -> None:
     """Undo durable ``headroom wrap grok`` MCP and guidance edits.
 
-    Grok API routing is session-scoped via ``GROK_CLI_CHAT_PROXY_BASE_URL`` and
-    does not require config restoration. This command removes Headroom MCP
-    servers from ``~/.grok/config.toml`` and strips injected RTK guidance from
-    the project ``AGENTS.md``.
+    Grok inference routing is session-scoped via ``GROK_MODELS_BASE_URL`` and
+    does not require config restoration. Native settings and authentication
+    routing stay unchanged. This command removes Headroom MCP servers from
+    ``~/.grok/config.toml`` and strips injected RTK guidance from the project
+    ``AGENTS.md``.
     """
     click.echo()
     click.echo("  ╔═══════════════════════════════════════════════╗")
diff --git a/headroom/providers/grok/runtime.py b/headroom/providers/grok/runtime.py
index eb9480312..2f4e150fb 100644
--- a/headroom/providers/grok/runtime.py
+++ b/headroom/providers/grok/runtime.py
@@ -8,7 +8,7 @@ from collections.abc import Mapping
 from headroom.proxy.project_context import with_project_prefix
 
 DEFAULT_API_URL = "https://api.x.ai"
-PROXY_ENV_KEY = "GROK_CLI_CHAT_PROXY_BASE_URL"
+PROXY_ENV_KEY = "GROK_MODELS_BASE_URL"
 
 
 def proxy_base_url(port: int) -> str:
@@ -23,9 +23,9 @@ def build_launch_env(
 ) -> tuple[dict[str, str], list[str]]:
     """Build environment variables for Grok CLI through the local proxy.
 
-    Grok routes inference traffic through ``GROK_CLI_CHAT_PROXY_BASE_URL``
-    when set (see Grok CLI auth/custom-models docs). The proxy forwards
-    OpenAI-compatible chat requests upstream to xAI.
+    Grok routes inference traffic through ``GROK_MODELS_BASE_URL`` when set.
+    The proxy forwards OpenAI-compatible chat requests upstream to xAI while
+    Grok keeps its native settings and authentication routing.
 
     ``project`` (the wrap launch directory) is encoded as a ``/p/<name>``
     base-URL prefix because Grok cannot send custom attribution headers;
diff --git a/tests/test_cli/test_wrap_grok.py b/tests/test_cli/test_wrap_grok.py
index 1cd278809..03053be81 100644
--- a/tests/test_cli/test_wrap_grok.py
+++ b/tests/test_cli/test_wrap_grok.py
@@ -44,6 +44,7 @@ def test_wrap_grok_sets_proxy_env(
     env = captured["env"]
     assert isinstance(env, dict)
     assert env[PROXY_ENV_KEY] == f"http://127.0.0.1:8787{_expected_project_prefix()}/v1"
+    assert "GROK_CLI_CHAT_PROXY_BASE_URL" not in env
     assert captured["tool_label"] == "GROK"
     assert captured["agent_type"] == "grok"
     assert captured["args"] == ("-p", "hello")
diff --git a/tests/test_provider_grok.py b/tests/test_provider_grok.py
index 08793332d..3af357ccd 100644
--- a/tests/test_provider_grok.py
+++ b/tests/test_provider_grok.py
@@ -8,10 +8,11 @@ def test_grok_proxy_base_url_uses_local_headroom_proxy() -> None:
     assert proxy_base_url(8787) == "http://127.0.0.1:8787/v1"
 
 
-def test_grok_build_launch_env_sets_chat_proxy_base_url() -> None:
+def test_grok_build_launch_env_sets_models_base_url() -> None:
     env, display = build_launch_env(9999, environ={})
 
     assert env[PROXY_ENV_KEY] == "http://127.0.0.1:9999/v1"
+    assert "GROK_CLI_CHAT_PROXY_BASE_URL" not in env
     assert display == [f"{PROXY_ENV_KEY}=http://127.0.0.1:9999/v1"]
 
 
@@ -19,6 +20,7 @@ def test_grok_build_launch_env_applies_project_prefix() -> None:
     env, _display = build_launch_env(8787, environ={}, project="frontend")
 
     assert env[PROXY_ENV_KEY] == "http://127.0.0.1:8787/p/frontend/v1"
+    assert "GROK_CLI_CHAT_PROXY_BASE_URL" not in env
 
 
 def test_grok_build_install_env_returns_proxy_url() -> None: