fix(vertex_ai): strip LiteLLM-internal keys from extra_body before merging to Gemini request

litellm/llms/vertex_ai/gemini/transformation.py

@@ -529,12 +529,18 @@ def _gemini_convert_messages_with_history(  # noqa: PLR0915
         raise e
 
 
+# Keys that LiteLLM consumes internally and must never be forwarded to the
+_LITELLM_INTERNAL_EXTRA_BODY_KEYS: frozenset = frozenset({"cache", "tags"})
+
+
 def _pop_and_merge_extra_body(data: RequestBody, optional_params: dict) -> None:
     """Pop extra_body from optional_params and shallow-merge into data, deep-merging dict values."""
     extra_body: Optional[dict] = optional_params.pop("extra_body", None)
     if extra_body is not None:
         data_dict: dict = data  # type: ignore[assignment]
         for k, v in extra_body.items():
+            if k in _LITELLM_INTERNAL_EXTRA_BODY_KEYS:
+                continue
             if k in data_dict and isinstance(data_dict[k], dict) and isinstance(v, dict):
                 data_dict[k].update(v)
             else:

litellm/model_prices_and_context_window_backup.json

@@ -16799,6 +16799,42 @@
         "supports_vision": true,
         "supports_web_search": true
     },
+    "gemini/gemini-3.1-flash-image-preview": {
+        "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token_batches": 1.25e-07,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.045,
+        "output_cost_per_image_token": 6e-05,
+        "output_cost_per_image_token_batches": 3e-05,
+        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token_batches": 7.5e-07,
+        "rpm": 1000,
+        "tpm": 4000000,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
     "gemini/deep-research-pro-preview-12-2025": {
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,

tests/test_litellm/llms/vertex_ai/gemini/test_vertex_ai_gemini_transformation.py

@@ -126,6 +126,75 @@ def test_vertex_ai_includes_labels():
 
 
 
+def test_extra_body_cache_not_forwarded_to_vertex_ai():
+    """
+    'cache' inside extra_body is a LiteLLM-internal proxy caching control.
+    It must NOT be forwarded to the Vertex AI request body.
+
+    Regression test for: "Invalid JSON payload received. Unknown name \"cache\": Cannot find field."
+    Vertex AI enforces a strict JSON schema and rejects any unknown field.
+    """
+    messages = [{"role": "user", "content": "test"}]
+    optional_params = {
+        "extra_body": {
+            "cache": {"use-cache": True, "ttl": 86400},  # LiteLLM-internal
+            "some_vertex_param": "value",                 # legitimate provider extra
+        },
+    }
+    litellm_params = {}
+
+    result = _transform_request_body(
+        messages=messages,
+        model="gemini-2.5-pro",
+        optional_params=optional_params,
+        custom_llm_provider="vertex_ai",
+        litellm_params=litellm_params,
+        cached_content=None,
+    )
+
+    # 'cache' must be stripped — Vertex AI has no such field
+    assert "cache" not in result, (
+        "extra_body.cache must not be forwarded to Vertex AI. "
+        "Vertex AI rejects it with 400: Unknown name \"cache\": Cannot find field."
+    )
+
+    # Other legitimate extra_body keys should still pass through
+    assert "some_vertex_param" in result
+    assert result["some_vertex_param"] == "value"
+
+    # Core request fields must be present
+    assert "contents" in result
+
+
+def test_extra_body_tags_not_forwarded_to_vertex_ai():
+    """
+    'tags' inside extra_body is a LiteLLM-internal param for logging/tracking.
+    It must NOT be forwarded to the Vertex AI request body.
+    Documented in litellm_proxy.md: "Send tags by including them in the extra_body parameter"
+    """
+    messages = [{"role": "user", "content": "test"}]
+    optional_params = {
+        "extra_body": {
+            "tags": ["user:alice", "env:prod"],
+            "custom_param": "allowed",
+        },
+    }
+    litellm_params = {}
+
+    result = _transform_request_body(
+        messages=messages,
+        model="gemini-2.5-pro",
+        optional_params=optional_params,
+        custom_llm_provider="vertex_ai",
+        litellm_params=litellm_params,
+        cached_content=None,
+    )
+
+    assert "tags" not in result
+    assert "custom_param" in result
+    assert result["custom_param"] == "allowed"
+
+
 def test_metadata_to_labels_vertex_only():
     """Test that metadata->labels conversion only happens for Vertex AI"""
     messages = [{"role": "user", "content": "test"}]