# Gemini 3.8 Live models now available on AI Gateway

Publisher-attributed story with a reviewed brief or permitted publisher paragraph. The original publisher is responsible for the linked reporting.

- Publisher: Vercel
- Author credit: Kevin Dawkins; Zachary Chen; Jerilyn Zheng
- Category: AI
- Original publication time: 2026-09-15T00:00:00Z
- Original update time: 2026-09-15T00:00:00Z
- First observed by NexusTechWire: 2026-10-01T20:28:47Z
- Original source: https://vercel.com/changelog/gemini-3-8-live-models-now-available-on-ai-gateway
- NexusTechWire record: https://nexustechwire.com/news/news-8d5e53f54636261e62f0

## The brief

Vercel added Google's Gemini 3.8 Live and Live Extended Thinking to AI Gateway for spoken conversations. Its announcement describes visual grounding, automatic switching among 97 languages and tool calls that can run while speech continues. Extended Thinking adds parallel multistep reasoning. Developers connect through the AI SDK realtime API using a short-lived token and a WebSocket connection.

AI-assisted NexusTechWire summary, checked against the linked source on 2026-10-02T00:20:08.158Z. Not independent reporting.

Read the full original: [Vercel](https://vercel.com/changelog/gemini-3-8-live-models-now-available-on-ai-gateway)

This record does not reproduce the complete article or represent independent confirmation of every source claim.