PulseAugur
EN
LIVE 18:05:15

Google, ElevenLabs deprecate AI models, reroute traffic in November 2026

By PulseAugur Editorial · [1 sources] ·

Several AI model providers, including Google and ElevenLabs, are implementing significant changes to their APIs and model offerings in November 2026. Google is deprecating older Gemini models like gemini-2.5-pro and gemini-2.5-flash, rerouting traffic to newer versions such as gemini-3.8-flash and gemini-3.5-flash-lite, with associated billing and API changes. ElevenLabs is also deprecating older GPT-5 variants and Claude Sonnet 4.5, migrating users to newer models and adjusting its Realtime API behavior. These changes can impact voice agents by altering voice characteristics, response times, and tool-calling capabilities without requiring explicit deployment by the user. AI

IMPACT Voice agents may experience changes in voice quality, response speed, and tool-calling capabilities due to automatic model updates from providers like Google and ElevenLabs.

RANK_REASON The item details practical changes to existing AI models and APIs that affect developers and users of voice agents, rather than a new model release or significant research breakthrough.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Google, ElevenLabs deprecate AI models, reroute traffic in November 2026

How we ranked this

Signal score
2 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item details practical changes to existing AI models and APIs that affect developers and users of voice agents, rather than a new model release or significant research breakthrough.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Piyush Sahoo ·

    Find the expiring model IDs in your voice agent before Nov 17

    <p>Most voice agents I see in production aren't one model. They're three or four: a speech-to-text model, an LLM, a TTS voice, often a fallback LLM, sometimes a realtime speech model doing all of it at once. Each one is a string in a config file somewhere.</p> <p>This month sever…

RELATED ENTITIES

RELATED TOPICS