fix: use /v1/realtime for gemini/ provider live model

The gemini/ prefix indicates Google AI Studio, which uses /v1/realtime endpoint (OpenAI-compatible), not /vertex_ai/live.
2025-12-15 19:58:25 -03:00 · 2025-12-15 19:58:25 -03:00 · ddf9598f30
commit ddf9598f30
parent 20a41a67d6
2 changed files with 2 additions and 2 deletions
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@ -14790,7 +14790,7 @@
        "rpm": 100000,
        "source": "https://ai.google.dev/gemini-api/docs/pricing",
        "supported_endpoints": [
-            "/vertex_ai/live"
+            "/v1/realtime"
        ],
        "supported_modalities": [
            "text",
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@ -14790,7 +14790,7 @@
        "rpm": 100000,
        "source": "https://ai.google.dev/gemini-api/docs/pricing",
        "supported_endpoints": [
-            "/vertex_ai/live"
+            "/v1/realtime"
        ],
        "supported_modalities": [
            "text",