{"slug": "gemini-3-8-live-models-now-available-on-ai-gateway", "title": "Gemini 3.8 Live models now available on AI Gateway", "summary": "Google's Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking models are now available on Vercel's AI Gateway, supporting real-time spoken interactions for voice assistants and audio-based applications. The google/gemini-3.8-live model offers real-time audio, visual grounding, automatic switching across 97 languages, and background tool calls, while google/gemini-3.8-live-extended-thinking adds multi-step reasoning that runs in parallel with speech. Both models are accessible through the AI SDK's realtime API via WebSocket connections.", "body_md": "[Gemini 3.8 Live](https://vercel.com/ai-gateway/models/gemini-3.8-live) and [Gemini 3.8 Live Extended Thinking](https://vercel.com/ai-gateway/models/gemini-3.8-live-extended-thinking) from Google are now available on AI Gateway.\n\nBoth models support real-time spoken interactions for voice assistants, conversational experiences, and applications that respond through audio.\n\n`google/gemini-3.8-live` supports real-time audio, visual grounding, automatic switching across 97 languages, and background tool calls while the conversation continues.\n\n`google/gemini-3.8-live-extended-thinking` adds multi-step reasoning that runs in parallel with speech, allowing it to acknowledge requests and narrate progress without interrupting the conversation.\n\nUse either model through the AI SDK's realtime API. Install the Gateway provider and a WebSocket client:\n\nMint a short-lived token, open the WebSocket, and use the model adapter to serialize and parse realtime events:\n\nSee the [realtime quickstart](https://vercel.com/docs/ai-gateway/getting-started/realtime) for more details on realtime events and WebSocket connections.\n\nTry [Gemini 3.8 Live](https://vercel.com/ai-gateway/models/gemini-3.8-live) or [Gemini 3.8 Live Extended Thinking](https://vercel.com/ai-gateway/models/gemini-3.8-live-extended-thinking) in the model playground.\n\nAI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime.", "url": "https://wpnews.pro/news/gemini-3-8-live-models-now-available-on-ai-gateway", "canonical_source": "https://vercel.com/changelog/gemini-3-8-live-models-now-available-on-ai-gateway", "published_at": "2026-09-15 00:00:00+00:00", "updated_at": "2026-09-15 17:50:59.404591+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-tools", "natural-language-processing"], "entities": ["Google", "Gemini 3.8 Live", "Gemini 3.8 Live Extended Thinking", "Vercel", "AI Gateway", "AI SDK"], "alternates": {"html": "https://wpnews.pro/news/gemini-3-8-live-models-now-available-on-ai-gateway", "markdown": "https://wpnews.pro/news/gemini-3-8-live-models-now-available-on-ai-gateway.md", "text": "https://wpnews.pro/news/gemini-3-8-live-models-now-available-on-ai-gateway.txt", "jsonld": "https://wpnews.pro/news/gemini-3-8-live-models-now-available-on-ai-gateway.jsonld"}}