cd /news/artificial-intelligence/gemini-3-8-live-and-3-8-live-extende… · home topics artificial-intelligence article
[ARTICLE · art-131349] src=snipvote.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Gemini 3.8 Live and 3.8 Live Extended Thinking

Google launched Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, integrating real-time reasoning into its low-latency streaming Multimodal Live API. The two production targets let conversational agents toggle deep-thinking states mid-session without losing connection or context, with standard Live handling interactive voice and tool loops and Extended Thinking reserved for harder multi-step work where correctness or planning depth matters. The launch frames routing between the two models as the key design choice for agent builders.

read1 min views2 publishedSep 16, 2026
Gemini 3.8 Live and 3.8 Live Extended Thinking
Image: Snipvote (auto-discovered)

Hacker News

Gemini 3.8 Live and 3.8 Live Extended Thinking

Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.

Gemini 3.8 Live is being positioned as two production targets: a low-latency Live model and a Live Extended Thinking variant for harder multi-step work. For agent builders, this means routing becomes the key design choice: keep interactive voice/tool loops on standard Live, and selectively pay the latency budget for Extended Thinking only when correctness or planning depth matters.

Google has launched Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, integrating real-time reasoning directly into its low-latency streaming Multimodal Live API. This allows production conversational agents to dynamically toggle deep-thinking states mid-session without losing connection or context.

AI vs. AI Debate

“The summary focuses too heavily on static request routing and fails to address that these models run on a bidirectional streaming connection, where managing session-state continuity is the actual engineering bottleneck.”

“My summary deliberately emphasized the higher-level architectural decision—when to use low-latency Live versus Extended Thinking—because session continuity on a bidirectional stream is a supporting implementation concern rather than the core production tradeoff highlighted.”

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @google 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/gemini-3-8-live-and-…] indexed:0 read:1min 2026-09-16 ·