diff --git a/agent/auxiliary_client.py b/agent/auxiliary_client.py
index 0de263c415d..4126994bb8c 100644
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -7,7 +7,7 @@ the best available backend without duplicating fallback logic.
 Resolution order for text tasks (auto mode):
   1. OpenRouter  (OPENROUTER_API_KEY)
   2. Nous Portal (~/.hermes/auth.json active provider)
-  3. Custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY)
+  3. Custom endpoint (config.yaml model.base_url + OPENAI_API_KEY)
   4. Codex OAuth (Responses API via chatgpt.com with gpt-5.3-codex,
      wrapped to look like a chat.completions client)
   5. Native Anthropic
@@ -584,15 +584,11 @@ def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
 
 
 def _read_main_model() -> str:
-    """Read the user's configured main model from config/env.
+    """Read the user's configured main model from config.yaml.
 
-    Falls back through HERMES_MODEL → LLM_MODEL → config.yaml model.default
-    so the auxiliary client can use the same model as the main agent when no
-    dedicated auxiliary model is available.
+    config.yaml model.default is the single source of truth for the active
+    model. Environment variables are no longer consulted.
     """
-    from_env = os.getenv("OPENAI_MODEL") or os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL")
-    if from_env:
-        return from_env.strip()
     try:
         from hermes_cli.config import load_config
         cfg = load_config()
diff --git a/cli.py b/cli.py
index c2d118193c3..cf2a5f8c862 100644
--- a/cli.py
+++ b/cli.py
@@ -1124,9 +1124,9 @@ class HermesCLI:
         self.acp_args: list[str] = []
         self.base_url = (
             base_url
-            or os.getenv("OPENAI_BASE_URL")
-            or os.getenv("OPENROUTER_BASE_URL", CLI_CONFIG["model"]["base_url"])
-        )
+            or CLI_CONFIG["model"].get("base_url", "")
+            or os.getenv("OPENROUTER_BASE_URL", "")
+        ) or None
         # Match key to resolved base_url: OpenRouter URL → prefer OPENROUTER_API_KEY,
         # custom endpoint → prefer OPENAI_API_KEY (issue #560).
         # Note: _ensure_runtime_credentials() re-resolves this before first use.
@@ -3239,7 +3239,7 @@ class HermesCLI:
                         print(f"      {mid}{current_marker}")
                 elif p["id"] == "custom":
                     from hermes_cli.models import _get_custom_base_url
-                    custom_url = _get_custom_base_url() or os.getenv("OPENAI_BASE_URL", "")
+                    custom_url = _get_custom_base_url()
                     if custom_url:
                         print(f"      endpoint: {custom_url}")
                     if is_active:
diff --git a/gateway/run.py b/gateway/run.py
index 9cc42b794d3..48f5182cb96 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -364,20 +364,19 @@ def _load_gateway_config() -> dict:
 
 
 def _resolve_gateway_model(config: dict | None = None) -> str:
-    """Read model from env/config — mirrors the resolution in _run_agent_sync.
+    """Read model from config.yaml — single source of truth.
 
     Without this, temporary AIAgent instances (memory flush, /compress) fall
     back to the hardcoded default which fails when the active provider is
     openai-codex.
     """
-    model = os.getenv("HERMES_MODEL") or os.getenv("LLM_MODEL") or ""
     cfg = config if config is not None else _load_gateway_config()
     model_cfg = cfg.get("model", {})
     if isinstance(model_cfg, str):
-        model = model_cfg
+        return model_cfg
     elif isinstance(model_cfg, dict):
-        model = model_cfg.get("default") or model_cfg.get("model") or model
-    return model
+        return model_cfg.get("default") or model_cfg.get("model") or ""
+    return ""
 
 
 def _resolve_hermes_bin() -> Optional[list[str]]:
@@ -2762,7 +2761,7 @@ class GatewayRunner:
                     {
                         "role": "session_meta",
                         "tools": tool_defs or [],
-                        "model": os.getenv("HERMES_MODEL", ""),
+                        "model": _resolve_gateway_model(),
                         "platform": source.platform.value if source.platform else "",
                         "timestamp": ts,
                     }
@@ -3227,9 +3226,11 @@ class GatewayRunner:
             except Exception:
                 current_provider = "openrouter"
 
-        # Detect custom endpoint
-        if current_provider == "openrouter" and os.getenv("OPENAI_BASE_URL", "").strip():
-            current_provider = "custom"
+        # Detect custom endpoint from config base_url
+        if current_provider == "openrouter":
+            _cfg_base = model_cfg.get("base_url", "") if isinstance(model_cfg, dict) else ""
+            if _cfg_base and "openrouter.ai" not in _cfg_base:
+                current_provider = "custom"
 
         current_label = _PROVIDER_LABELS.get(current_provider, current_provider)
 
diff --git a/hermes_cli/main.py b/hermes_cli/main.py
index 9dca2105638..3bd6afa54f7 100644
--- a/hermes_cli/main.py
+++ b/hermes_cli/main.py
@@ -1050,10 +1050,6 @@ def _model_flow_openrouter(config, current_model=""):
 
     selected = _prompt_model_selection(openrouter_models, current_model=current_model)
     if selected:
-        # Clear any custom endpoint and set provider to openrouter
-        if get_env_value("OPENAI_BASE_URL"):
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _save_model_choice(selected)
 
         # Update config provider and deactivate any OAuth provider
@@ -1143,10 +1139,6 @@ def _model_flow_nous(config, current_model=""):
         # Reactivate Nous as the provider and update config
         inference_url = creds.get("base_url", "")
         _update_config_for_provider("nous", inference_url)
-        # Clear any custom endpoint that might conflict
-        if get_env_value("OPENAI_BASE_URL"):
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         print(f"Default model set to: {selected} (via Nous Portal)")
     else:
         print("No change.")
@@ -1191,10 +1183,6 @@ def _model_flow_openai_codex(config, current_model=""):
     if selected:
         _save_model_choice(selected)
         _update_config_for_provider("openai-codex", DEFAULT_CODEX_BASE_URL)
-        # Clear custom endpoint env vars that would otherwise override Codex.
-        if get_env_value("OPENAI_BASE_URL"):
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         print(f"Default model set to: {selected} (via OpenAI Codex)")
     else:
         print("No change.")
@@ -1275,11 +1263,6 @@ def _model_flow_custom(config):
         if probe.get("suggested_base_url"):
             print(f"  If this server expects /v1, try base URL: {probe['suggested_base_url']}")
 
-    if base_url:
-        save_env_value("OPENAI_BASE_URL", effective_url)
-    if api_key:
-        save_env_value("OPENAI_API_KEY", api_key)
-
     if model_name:
         _save_model_choice(model_name)
 
@@ -1439,9 +1422,6 @@ def _model_flow_named_custom(config, provider_info):
 
     # If a model is saved, just activate immediately — no probing needed
     if saved_model:
-        save_env_value("OPENAI_BASE_URL", base_url)
-        if api_key:
-            save_env_value("OPENAI_API_KEY", api_key)
         _save_model_choice(saved_model)
 
         cfg = load_config()
@@ -1513,9 +1493,6 @@ def _model_flow_named_custom(config, provider_info):
             return
 
     # Activate and save the model to the custom_providers entry
-    save_env_value("OPENAI_BASE_URL", base_url)
-    if api_key:
-        save_env_value("OPENAI_API_KEY", api_key)
     _save_model_choice(model_name)
 
     cfg = load_config()
@@ -1829,11 +1806,6 @@ def _model_flow_copilot(config, current_model=""):
             catalog=catalog,
             api_key=api_key,
         ) or selected
-        # Clear stale custom-endpoint overrides so the Copilot provider wins cleanly.
-        if get_env_value("OPENAI_BASE_URL"):
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
-
         initial_cfg = load_config()
         current_effort = _current_reasoning_effort(initial_cfg)
         reasoning_efforts = github_model_reasoning_efforts(
@@ -2058,11 +2030,6 @@ def _model_flow_kimi(config, current_model=""):
             selected = None
 
     if selected:
-        # Clear custom endpoint if set (avoid confusion)
-        if get_env_value("OPENAI_BASE_URL"):
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
-
         _save_model_choice(selected)
 
         # Update config with provider and base URL
@@ -2165,11 +2132,6 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
             selected = None
 
     if selected:
-        # Clear custom endpoint if set (avoid confusion)
-        if get_env_value("OPENAI_BASE_URL"):
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
-
         _save_model_choice(selected)
 
         # Update config with provider and base URL
@@ -2381,11 +2343,6 @@ def _model_flow_anthropic(config, current_model=""):
             selected = None
 
     if selected:
-        # Clear custom endpoint if set
-        if get_env_value("OPENAI_BASE_URL"):
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
-
         _save_model_choice(selected)
 
         # Update config with provider — clear base_url since
diff --git a/hermes_cli/models.py b/hermes_cli/models.py
index ed36823e419..5e1077837dd 100644
--- a/hermes_cli/models.py
+++ b/hermes_cli/models.py
@@ -349,7 +349,7 @@ def list_available_providers() -> list[dict[str, str]]:
         try:
             from hermes_cli.auth import get_auth_status, has_usable_secret
             if pid == "custom":
-                custom_base_url = _get_custom_base_url() or os.getenv("OPENAI_BASE_URL", "")
+                custom_base_url = _get_custom_base_url() or ""
                 has_creds = bool(custom_base_url.strip())
             elif pid == "openrouter":
                 has_creds = has_usable_secret(os.getenv("OPENROUTER_API_KEY", ""))
diff --git a/hermes_cli/runtime_provider.py b/hermes_cli/runtime_provider.py
index 0c82805d5af..644331baa61 100644
--- a/hermes_cli/runtime_provider.py
+++ b/hermes_cli/runtime_provider.py
@@ -229,28 +229,22 @@ def _resolve_openrouter_runtime(
     requested_norm = (requested_provider or "").strip().lower()
     cfg_provider = cfg_provider.strip().lower()
 
-    env_openai_base_url = os.getenv("OPENAI_BASE_URL", "").strip()
     env_openrouter_base_url = os.getenv("OPENROUTER_BASE_URL", "").strip()
 
+    # Use config base_url when available and the provider context matches.
+    # OPENAI_BASE_URL env var is no longer consulted — config.yaml is
+    # the single source of truth for endpoint URLs.
     use_config_base_url = False
     if cfg_base_url.strip() and not explicit_base_url:
         if requested_norm == "auto":
-            if (not cfg_provider or cfg_provider == "auto") and not env_openai_base_url:
+            if not cfg_provider or cfg_provider == "auto":
                 use_config_base_url = True
         elif requested_norm == "custom" and cfg_provider == "custom":
-            # provider: custom — use base_url from config (Fixes #1760).
             use_config_base_url = True
 
-    # When the user explicitly requested the openrouter provider, skip
-    # OPENAI_BASE_URL — it typically points to a custom / non-OpenRouter
-    # endpoint and would prevent switching back to OpenRouter (#874).
-    skip_openai_base = requested_norm == "openrouter"
-
-    # For custom, prefer config base_url over env so config.yaml is honored (#1760).
     base_url = (
         (explicit_base_url or "").strip()
         or (cfg_base_url.strip() if use_config_base_url else "")
-        or ("" if skip_openai_base else env_openai_base_url)
         or env_openrouter_base_url
         or OPENROUTER_BASE_URL
     ).rstrip("/")
diff --git a/hermes_cli/setup.py b/hermes_cli/setup.py
index 503c2bcdee8..648876d92fe 100644
--- a/hermes_cli/setup.py
+++ b/hermes_cli/setup.py
@@ -941,10 +941,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear any custom endpoint if switching to OpenRouter
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
 
         # Update config.yaml and deactivate any OAuth provider so the
         # resolver doesn't keep returning the old provider (e.g. Codex).
@@ -1032,10 +1028,6 @@ def setup_model_provider(config: dict):
 
             mock_args = argparse.Namespace()
             _login_openai_codex(mock_args, PROVIDER_REGISTRY["openai-codex"])
-            # Clear custom endpoint vars that would override provider routing.
-            if existing_custom:
-                save_env_value("OPENAI_BASE_URL", "")
-                save_env_value("OPENAI_API_KEY", "")
             _update_config_for_provider("openai-codex", DEFAULT_CODEX_BASE_URL)
             _set_model_provider(config, "openai-codex", DEFAULT_CODEX_BASE_URL)
         except SystemExit:
@@ -1118,10 +1110,6 @@ def setup_model_provider(config: dict):
                     "  If you get billing errors, check your plan at https://open.bigmodel.cn/"
                 )
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "zai", zai_base_url)
         selected_base_url = zai_base_url
 
@@ -1151,10 +1139,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "kimi-coding", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1184,10 +1168,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "minimax", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1217,10 +1197,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "minimax-cn", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1250,10 +1226,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "kilocode", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1352,10 +1324,6 @@ def setup_model_provider(config: dict):
                 else:
                     print_warning("Skipped — agent won't work without credentials")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         # Don't save base_url for Anthropic — resolve_runtime_provider()
         # always hardcodes it. Stale base_urls contaminate other providers.
         _set_model_provider(config, "anthropic")
@@ -1386,10 +1354,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _update_config_for_provider("ai-gateway", pconfig.inference_base_url, default_model="anthropic/claude-opus-4.6")
         _set_model_provider(config, "ai-gateway", pconfig.inference_base_url)
 
@@ -1418,10 +1382,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _update_config_for_provider("alibaba", pconfig.inference_base_url, default_model="qwen3.5-plus")
         _set_model_provider(config, "alibaba", pconfig.inference_base_url)
 
@@ -1451,10 +1411,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "opencode-zen", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1484,10 +1440,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without an API key")
 
-        # Clear custom endpoint vars if switching
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "opencode-go", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1518,9 +1470,6 @@ def setup_model_provider(config: dict):
             else:
                 print_warning("Skipped - agent won't work without a GitHub token or gh auth login")
 
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "copilot", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1534,9 +1483,6 @@ def setup_model_provider(config: dict):
         print_info(f"Base marker: {pconfig.inference_base_url}")
         print()
 
-        if existing_custom:
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "copilot-acp", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1553,9 +1499,6 @@ def setup_model_provider(config: dict):
         api_key = prompt("  HF Token", password=True)
         if api_key:
             save_env_value("HF_TOKEN", api_key)
-            # Clear OpenRouter env vars to prevent routing confusion
-            save_env_value("OPENAI_BASE_URL", "")
-            save_env_value("OPENAI_API_KEY", "")
         _set_model_provider(config, "huggingface", pconfig.inference_base_url)
         selected_base_url = pconfig.inference_base_url
 
@@ -1632,7 +1575,9 @@ def setup_model_provider(config: dict):
             _oai_key = prompt(_api_key_label, password=True).strip()
             if _oai_key:
                 save_env_value("OPENAI_API_KEY", _oai_key)
-                save_env_value("OPENAI_BASE_URL", _base_url)
+                # Save vision base URL to config (not .env — only secrets go there)
+                _vaux = config.setdefault("auxiliary", {}).setdefault("vision", {})
+                _vaux["base_url"] = _base_url
                 if "api.openai.com" in _base_url.lower():
                     _oai_vision_models = ["gpt-4o", "gpt-4o-mini", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano"]
                     _vm_choices = _oai_vision_models + ["Use default (gpt-4o-mini)"]
diff --git a/hermes_cli/tools_config.py b/hermes_cli/tools_config.py
index 337b67fe8ff..8b443d5dc28 100644
--- a/hermes_cli/tools_config.py
+++ b/hermes_cli/tools_config.py
@@ -983,8 +983,13 @@ def _configure_simple_requirements(ts_key: str):
             key_label = "    OPENAI_API_KEY" if "api.openai.com" in base_url.lower() else "    API key"
             api_key = _prompt(key_label, password=True)
             if api_key and api_key.strip():
-                save_env_value("OPENAI_BASE_URL", base_url)
                 save_env_value("OPENAI_API_KEY", api_key.strip())
+                # Save vision base URL to config (not .env — only secrets go there)
+                from hermes_cli.config import load_config, save_config
+                _cfg = load_config()
+                _aux = _cfg.setdefault("auxiliary", {}).setdefault("vision", {})
+                _aux["base_url"] = base_url
+                save_config(_cfg)
                 if "api.openai.com" in base_url.lower():
                     save_env_value("AUXILIARY_VISION_MODEL", "gpt-4o-mini")
                 _print_success("    Saved")
diff --git a/tests/agent/test_auxiliary_client.py b/tests/agent/test_auxiliary_client.py
index 35dcee7ad65..a8197e57440 100644
--- a/tests/agent/test_auxiliary_client.py
+++ b/tests/agent/test_auxiliary_client.py
@@ -465,9 +465,16 @@ class TestGetTextAuxiliaryClient:
         assert model == "google/gemini-3-flash-preview"
 
     def test_custom_endpoint_over_codex(self, monkeypatch, codex_auth_dir):
-        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:1234/v1")
+        config = {
+            "model": {
+                "provider": "custom",
+                "base_url": "http://localhost:1234/v1",
+                "default": "my-local-model",
+            }
+        }
         monkeypatch.setenv("OPENAI_API_KEY", "lm-studio-key")
-        monkeypatch.setenv("OPENAI_MODEL", "my-local-model")
+        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
+        monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
         # Override the autouse monkeypatch for codex
         monkeypatch.setattr(
             "agent.auxiliary_client._read_codex_access_token",
@@ -726,10 +733,17 @@ class TestVisionClientFallback:
 
     def test_vision_forced_main_uses_custom_endpoint(self, monkeypatch):
         """When explicitly forced to 'main', vision CAN use custom endpoint."""
+        config = {
+            "model": {
+                "provider": "custom",
+                "base_url": "http://localhost:1234/v1",
+                "default": "my-local-model",
+            }
+        }
         monkeypatch.setenv("AUXILIARY_VISION_PROVIDER", "main")
-        monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:1234/v1")
         monkeypatch.setenv("OPENAI_API_KEY", "local-key")
-        monkeypatch.setenv("OPENAI_MODEL", "my-local-model")
+        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
+        monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
         with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
              patch("agent.auxiliary_client.OpenAI") as mock_openai:
             client, model = get_vision_auxiliary_client()
@@ -827,9 +841,16 @@ class TestResolveForcedProvider:
         assert model is None
 
     def test_forced_main_uses_custom(self, monkeypatch):
-        monkeypatch.setenv("OPENAI_BASE_URL", "http://local:8080/v1")
+        config = {
+            "model": {
+                "provider": "custom",
+                "base_url": "http://local:8080/v1",
+                "default": "my-local-model",
+            }
+        }
         monkeypatch.setenv("OPENAI_API_KEY", "local-key")
-        monkeypatch.setenv("OPENAI_MODEL", "my-local-model")
+        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
+        monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
         with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
              patch("agent.auxiliary_client.OpenAI") as mock_openai:
             client, model = _resolve_forced_provider("main")
@@ -858,10 +879,17 @@ class TestResolveForcedProvider:
 
     def test_forced_main_skips_openrouter_nous(self, monkeypatch):
         """Even if OpenRouter key is set, 'main' skips it."""
+        config = {
+            "model": {
+                "provider": "custom",
+                "base_url": "http://local:8080/v1",
+                "default": "my-local-model",
+            }
+        }
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
-        monkeypatch.setenv("OPENAI_BASE_URL", "http://local:8080/v1")
         monkeypatch.setenv("OPENAI_API_KEY", "local-key")
-        monkeypatch.setenv("OPENAI_MODEL", "my-local-model")
+        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
+        monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
         with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
              patch("agent.auxiliary_client.OpenAI") as mock_openai:
             client, model = _resolve_forced_provider("main")
diff --git a/tests/hermes_cli/test_setup_model_provider.py b/tests/hermes_cli/test_setup_model_provider.py
index 0acbfea512f..76ba943741d 100644
--- a/tests/hermes_cli/test_setup_model_provider.py
+++ b/tests/hermes_cli/test_setup_model_provider.py
@@ -129,16 +129,13 @@ def test_setup_custom_endpoint_saves_working_v1_base_url(tmp_path, monkeypatch):
 
     env = _read_env(tmp_path)
 
-    # _model_flow_custom saves env vars and config to disk
-    assert env.get("OPENAI_BASE_URL") == "http://localhost:8000/v1"
-    assert env.get("OPENAI_API_KEY") == "local-key"
-
-    # The model config is saved as a dict by _model_flow_custom
+    # _model_flow_custom saves config to disk (base_url in config, not .env)
     reloaded = load_config()
     model_cfg = reloaded.get("model", {})
     if isinstance(model_cfg, dict):
         assert model_cfg.get("provider") == "custom"
         assert model_cfg.get("default") == "llm"
+        assert model_cfg.get("base_url") == "http://localhost:8000/v1"
 
 
 def test_setup_keep_current_config_provider_uses_provider_specific_model_menu(tmp_path, monkeypatch):
@@ -232,8 +229,11 @@ def test_setup_keep_current_anthropic_can_configure_openai_vision_default(tmp_pa
     env = _read_env(tmp_path)
 
     assert env.get("OPENAI_API_KEY") == "sk-openai"
-    assert env.get("OPENAI_BASE_URL") == "https://api.openai.com/v1"
     assert env.get("AUXILIARY_VISION_MODEL") == "gpt-4o-mini"
+    # Vision base URL saved to config.yaml, not .env
+    reloaded = load_config()
+    vision_cfg = reloaded.get("auxiliary", {}).get("vision", {})
+    assert vision_cfg.get("base_url") == "https://api.openai.com/v1"
 
 
 def test_setup_copilot_uses_gh_auth_and_saves_provider(tmp_path, monkeypatch):
@@ -433,8 +433,7 @@ def test_setup_switch_custom_to_codex_clears_custom_endpoint_and_updates_config(
     env = _read_env(tmp_path)
     reloaded = load_config()
 
-    assert env.get("OPENAI_BASE_URL") == ""
-    assert env.get("OPENAI_API_KEY") == ""
+    # OPENAI_BASE_URL is no longer written/cleared in .env — config is authoritative
     assert reloaded["model"]["provider"] == "openai-codex"
     assert reloaded["model"]["default"] == "openai/gpt-5.3-codex"
     assert reloaded["model"]["base_url"] == "https://chatgpt.com/backend-api/codex"
diff --git a/tests/test_cli_provider_resolution.py b/tests/test_cli_provider_resolution.py
index b9960f08c2c..943a45a5582 100644
--- a/tests/test_cli_provider_resolution.py
+++ b/tests/test_cli_provider_resolution.py
@@ -467,6 +467,6 @@ def test_model_flow_custom_saves_verified_v1_base_url(monkeypatch, capsys):
     output = capsys.readouterr().out
 
     assert "Saving the working base URL instead" in output
-    assert saved_env["OPENAI_BASE_URL"] == "http://localhost:8000/v1"
-    assert saved_env["OPENAI_API_KEY"] == "local-key"
+    # OPENAI_BASE_URL is no longer saved to .env — config.yaml is authoritative
+    assert "OPENAI_BASE_URL" not in saved_env
     assert saved_env["MODEL"] == "llm"
\ No newline at end of file