diff --git a/gemini/README.md b/gemini/README.md
index 484975c..9409478 100644
--- a/gemini/README.md
+++ b/gemini/README.md
@@ -49,14 +49,15 @@ gemini models
 | `gemini-3.5-flash` | Gemini 3.5 Flash |
 | `gemini-3-flash-preview` | Gemini 3 Flash Preview |
 | `gemini-3.1-flash-lite-preview` | Gemini 3.1 Flash Lite Preview |
-| `gemini-3.1-flash-image` | Gemini 3.1 Flash Image |
-| `gemini-3-pro-image` | Gemini 3 Pro Image |
 | `gemini-2.5-pro` | Gemini 2.5 Pro |
 | `gemini-2.5-flash` | Gemini 2.5 Flash (default) |
 | `gemini-2.5-flash-lite` | Gemini 2.5 Flash Lite |
-| `gemini-2.5-flash-image` | Gemini 2.5 Flash Image |
 | `gemini-2.0-flash` | Gemini 2.0 Flash |
 
+> Image-generating models (`gemini-*-image`) are not available on the chat
+> endpoint. Use the native `/v1beta/models/{model}:generateContent` API for
+> image generation.
+
 ## Available Video Models
 
 | Model | Notes |
diff --git a/gemini/gemini_cli/core/output.py b/gemini/gemini_cli/core/output.py
index 95afdfe..16b06ba 100644
--- a/gemini/gemini_cli/core/output.py
+++ b/gemini/gemini_cli/core/output.py
@@ -17,12 +17,9 @@
     "gemini-3.5-flash",
     "gemini-3-flash-preview",
     "gemini-3.1-flash-lite-preview",
-    "gemini-3.1-flash-image",
-    "gemini-3-pro-image",
     "gemini-2.5-pro",
     "gemini-2.5-flash",
     "gemini-2.5-flash-lite",
-    "gemini-2.5-flash-image",
     "gemini-2.0-flash",
 ]
 
diff --git a/gemini/tests/test_commands.py b/gemini/tests/test_commands.py
index 5da4427..17c832d 100644
--- a/gemini/tests/test_commands.py
+++ b/gemini/tests/test_commands.py
@@ -98,9 +98,6 @@ def test_chat_with_new_models(self, runner, mock_chat_response):
         for model in [
             "gemini-2.5-flash-lite",
             "gemini-3.1-flash-lite-preview",
-            "gemini-3.1-flash-image",
-            "gemini-2.5-flash-image",
-            "gemini-3-pro-image",
         ]:
             respx.post("https://api.acedata.cloud/gemini/chat/completions").mock(
                 return_value=Response(200, json=mock_chat_response)
@@ -110,6 +107,18 @@ def test_chat_with_new_models(self, runner, mock_chat_response):
             )
             assert result.exit_code == 0, f"Model {model} failed: {result.output}"
 
+    def test_chat_rejects_image_models(self, runner):
+        """Image models are native-only; the chat endpoint can't serve them."""
+        for model in [
+            "gemini-3.1-flash-image",
+            "gemini-2.5-flash-image",
+            "gemini-3-pro-image",
+        ]:
+            result = runner.invoke(
+                cli, ["--token", "test-token", "chat", "Hello", "-m", model, "--json"]
+            )
+            assert result.exit_code != 0, f"Model {model} should be rejected"
+
     @respx.mock
     def test_chat_with_max_completion_tokens(self, runner, mock_chat_response):
         respx.post("https://api.acedata.cloud/gemini/chat/completions").mock(