{
  "schema_version": "1.1",
  "id": "s4:https://vercel.com/changelog/gemini-3-8-live-models-now-available-on-ai-gateway",
  "slug": "gemini-3-8-live-models-now-available-on-ai-gateway-14yndjj",
  "url": "https://feed7.dev/p/gemini-3-8-live-models-now-available-on-ai-gateway-14yndjj",
  "title": "Gemini 3.8 Live models now available on AI Gateway",
  "why_included": "Two Gemini 3.8 Live models add real-time audio to AI Gateway; the extended variant can reason alongside speech while the base model keeps tool calls in the background.",
  "summary": "AI Gateway now exposes **Gemini 3.8 Live** and **Gemini 3.8 Live Extended Thinking** through the AI SDK's realtime API. Both handle spoken interaction; the base model adds visual grounding, background tool calls, and switching across **97 languages**.",
  "practical_implication": "For voice agents, use short-lived tokens and the supplied WebSocket adapter, then choose the extended model only when multi-step reasoning must continue alongside speech. Gateway can centralize usage, cost, retries, and failover.",
  "agent_context": "AI Gateway now exposes **Gemini 3.8 Live** and **Gemini 3.8 Live Extended Thinking** through the AI SDK's realtime API. Both handle spoken interaction; the base model adds visual grounding, background tool calls, and switching across **97 languages**.\n\nFor voice agents, use short-lived tokens and the supplied WebSocket adapter, then choose the extended model only when multi-step reasoning must continue alongside speech. Gateway can centralize usage, cost, retries, and failover.\n\nThe material gives no latency, pricing, or quality measurements, and realtime support is exposed through an **experimental API**. Extended Thinking also requires choosing exactly one thinking control: level or budget.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/gemini-3-8-live-models-now-available-on-ai-gateway",
    "published_at": "2026-09-15T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "model",
  "domains": [
    "audio"
  ],
  "topics": [
    "reasoning",
    "tool-use"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The material gives no latency, pricing, or quality measurements, and realtime support is exposed through an **experimental API**. Extended Thinking also requires choosing exactly one thinking control: level or budget."
  ],
  "connected_context": {
    "meaning": "This broadens realtime voice routing with visual grounding, background tools, multilingual switching, and an explicit choice between ordinary and extended reasoning. Against existing live models, it makes concurrent speech-and-work capability a selectable architecture rather than a unique feature. Missing latency, cost, and quality measurements—and the experimental API—leave model choice dependent on matched voice workloads.",
    "corpus_size": 807,
    "generated_at": "2026-09-18T10:05:03.869Z",
    "connections": [
      {
        "title": "Grok Voice Think Fast 2.0 now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/grok-voice-think-fast-2-0-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/grok-voice-think-fast-2-0-now-available-on-ai-gateway-1dacr27",
        "reason": "Grok is a direct realtime speech-and-tool competitor; together they make interruption behavior, tool-call timing, noisy-input handling, credential design, and measured latency relevant comparison points."
      },
      {
        "title": "GPT-Live 1 now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/gpt-live-1-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/gpt-live-1-now-available-on-ai-gateway-18x7ban",
        "reason": "Both support speech alongside deeper work, but GPT-Live-1 delegates that work to a separately chosen text model while Gemini offers an Extended Thinking live variant, creating distinct architectures to evaluate."
      },
      {
        "title": "Gemini 3.8 Flash now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/gemini-3-8-flash-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/gemini-3-8-flash-now-available-on-ai-gateway-0cun77q",
        "reason": "Gemini 3.8 Flash already makes thinking behavior an evaluation variable for latency and token use; the live release sharpens that requirement by forcing exactly one extended-thinking control while speech continues."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-15T00:00:00.000Z",
  "modified_at": "2026-09-15T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/gemini-3-8-live-models-now-available-on-ai-gateway-14yndjj",
    "json": "https://feed7.dev/p/gemini-3-8-live-models-now-available-on-ai-gateway-14yndjj.json",
    "markdown": "https://feed7.dev/p/gemini-3-8-live-models-now-available-on-ai-gateway-14yndjj.md"
  }
}