when will this be available to be used in Vapi?

Hi hacheng1, We already support Gemini 2.0 flash variants and newer ones per the changelog: - gemini-2.0-flash-exp and gemini-2.0-flash-realtime-exp: added Jan 7, 2025 (supports realtimeConfig and speech/voiceConfig). See https://docs.vapi.ai/changelog/2025/1/7 - gemini-2.0-flash-lite: added Mar 15, 2025. See https://docs.vapi.ai/changelog/2025/3/15 - gemini-2.5-flash-preview-05-20: added May 24, 2025. See https://docs.vapi.ai/changelog/2025/5/24 If you mean a newer Gemini release (e.g., Gemini 3 Flash), we don’t have it listed yet; when we add a model it will appear in the changelog and the assistant model dropdown. Tell me which exact model you need (e.g., "gemini-3-flash") and whether you need realtime/voice/transcription support so I can relay priority to the platform team.

The model is "gemini-3-flash-preview" — would be great if you could prioritize adding it. Gemini 2.5 Flash is already popular for voice agents given its low latency and solid performance, and 3-flash is supposed to be a meaningful upgrade. Looks like there are a number of other people also requesting it to be added ASAP. Docs here: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemini-3-flash-preview?pli=1&rapt=AEjHL4OSOdFdshO7VzkGaVWyp7O8ZS9_Fip7v_EC1ect4yVTk4gozvu53Ij9m8stqlCR-wujAeI0dNmmDityR_T_nBJOujsyScjM9Z54ITflPWXBwxjsj2w

Hey, Google’s Gemini 3 models are currently in preview, so we’re not adding native Gemini‑3 support in Vapi during this phase. In the meantime, if you already have access to Gemini 3 through a provider like Together AI / your own stack, you can still use it with Vapi via a Custom LLM server, which is how we currently recommend plugging in models we don’t natively host yet. Kind Regards, Sarthak Vaish