fix(helicone): add Gemini/Vertex AI support to HeliconeLogger

- Add "gemini" to helicone_model_list so Gemini models are recognized
- Use /custom/v1/log endpoint for Gemini models instead of /oai/v1/log
- Set correct provider_url for Google's generativelanguage API
- Add unit test for Gemini model recognition

Previously, Gemini models were logged as "gpt-3.5-turbo" with OpenAI
as the provider, corrupting analytics. Now they log correctly with
their actual model name and CUSTOM provider.

litellm/integrations/helicone.py

@@ -11,6 +11,7 @@ class HeliconeLogger:
     helicone_model_list = [
         "gpt",
         "claude",
+        "gemini",
         "command-r",
         "command-r-plus",
         "command-light",
@@ -151,6 +152,9 @@ class HeliconeLogger:
             if "claude" in model:
                 url = f"{self.api_base}/anthropic/v1/log"
                 provider_url = "https://api.anthropic.com/v1/messages"
+            elif "gemini" in model:
+                url = f"{self.api_base}/custom/v1/log"
+                provider_url = "https://generativelanguage.googleapis.com/v1beta"
             headers = {
                 "Authorization": f"Bearer {self.key}",
                 "Content-Type": "application/json",

tests/local_testing/test_helicone_integration.py

@@ -162,3 +162,27 @@ def test_helicone_removes_otel_span_from_metadata():
     assert result_metadata["other_metadata"] == "some_value"
     
     print("✅ Test passed: litellm_parent_otel_span was successfully removed from metadata")
+
+
+def test_helicone_gemini_model_in_list():
+    """
+    Test that Gemini models are in the helicone_model_list and use the correct endpoint.
+    Fixes: https://github.com/BerriAI/litellm/issues/19093
+    """
+    from litellm.integrations.helicone import HeliconeLogger
+
+    logger = HeliconeLogger()
+
+    # Test that "gemini" is in the model list
+    assert "gemini" in logger.helicone_model_list, "gemini should be in helicone_model_list"
+
+    # Test that gemini models are recognized (not replaced with gpt-3.5-turbo)
+    test_models = ["gemini-1.5-pro", "gemini-2.0-flash", "vertex_ai/gemini-1.5-flash"]
+    for model in test_models:
+        is_recognized = any(
+            accepted_model in model
+            for accepted_model in logger.helicone_model_list
+        )
+        assert is_recognized, f"{model} should be recognized by helicone_model_list"
+
+    print("✅ Test passed: Gemini models are properly supported in HeliconeLogger")