{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/gemini-3-8-live/","md":"https://postcutoff.com/m/gemini-3-8-live/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"gemini-3-8-live","name":"Gemini 3.8 Live","org":"Google DeepMind","family":"Gemini 3","released":"2026-09-15","status":"current","type":"audio/speech","modality_in":["text","image","audio","video"],"modality_out":["text","audio"],"open_weights":false,"model_license":"proprietary","context_window":131072,"max_output":65536,"knowledge_cutoff":null,"pricing":{"input":0.75,"output":4.5,"audio_input":3,"audio_output":12,"unit":"per 1M tokens (text in $0.75, text out $4.50; audio in $3.00 = ~$0.005/min, audio out $12.00 = ~$0.018/min)","source":"https://ai.google.dev/gemini-api/docs/pricing"},"price_line":"$0.75 in, $4.50 out per 1M tokens","access":[{"provider":"Gemini Live API (WebSocket)","model_id":"gemini-3.8-live","endpoint":"wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent","docs":"https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live"},{"provider":"Gemini Live API (WebSocket)","model_id":"gemini-3.8-live-extended-thinking","docs":"https://ai.google.dev/gemini-api/docs/live-api"},{"provider":"Web app","url":"https://gemini.google.com"}],"capabilities":[{"name":"Real-time multilingual voice agents","detail":"Low-latency speech-to-speech with near-real-time visual grounding; 97 languages with mid-conversation switching.","first":false,"discovered":"launch","source":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/"},{"name":"Asynchronous tool use while talking","detail":"Keeps the conversation going while tools run in the background, narrating progress ('Let me check that...').","first":false,"discovered":"launch","source":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/"},{"name":"Extended Thinking variant tops S2S quality","detail":"gemini-3.8-live-extended-thinking ranked #1 on Artificial Analysis Speech-to-Speech Quality Index (82.6) and 97.7% Big Bench Audio.","first":false,"discovered":"launch","source":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/"}],"entry":null,"notes":"Default Live API model; thinking_level not supported on gemini-3.8-live (use gemini-3.8-live-extended-thinking for deeper reasoning; pricing page lists it at the same rates as gemini-3.8-live, checked 2026-09-29). Previous: gemini-3.1-flash-live-preview, gemini-2.5-flash-native-audio-preview-12-2025. WebSocket endpoint is the standard Live API URL, not re-read today.","verified":"2026-09-29","body_md":"Native-audio model for real-time voice and video agents via the Live API (WebSocket, bidirectional streaming).\n\n```python\nfrom google import genai\nclient = genai.Client()\nasync with client.aio.live.connect(model=\"gemini-3.8-live\",\n        config={\"response_modalities\": [\"AUDIO\"]}) as session:\n    await session.send_client_content(turns={\"parts\": [{\"text\": \"Hi!\"}]})\n```\n\nSources: [model page](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live), [pricing](https://ai.google.dev/gemini-api/docs/pricing), [launch blog](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/).","page_url":"https://postcutoff.com/m/gemini-3-8-live/","standing":{"kind":"speech and audio","newer_count":25,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"gemini-3-5-transcribe","name":"Gemini 3.5 Transcribe (and Transcribe Live)","org":"Google DeepMind","released":"2026-08-26","page_url":"https://postcutoff.com/m/gemini-3-5-transcribe/"},"after":{"id":"gemini-3-8-flash-lite-tts","name":"Gemini 3.8 Flash-Lite TTS","org":"Google DeepMind","released":"2026-09-22","page_url":"https://postcutoff.com/m/gemini-3-8-flash-lite-tts/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}