# Gemini 3.8 Live Extended Thinking

Google, released 2026-09-15

**Verdict: recommended.** Gemini 3.8 Live Extended Thinking is the voice-agent model to start with: it tops Artificial Analysis' Speech to Speech Index and reasons and calls tools in the background while it keeps talking, at the same rate as the default Gemini 3.8 Live. The caveat is the Live API surface: no structured outputs, caching, code execution or batch. Right for teams building real-time voice agents that must solve multi-step problems mid-call. Last verified 2026-09-18.

## Pricing

- Input: $0.75 / 1M (text)
- Output: $4.50 / 1M (text)
- Context: 131K in, 65K out; audio $3/$12 per 1M

## Strengths

- Real-time voice agents that must reason through multi-step problems mid-conversation
- Calling tools and APIs in the background while the conversation continues
- Multilingual voice: Google says it detects and switches between 97 languages mid-conversation
- Workloads that need structured outputs, context caching, code execution or the Batch API, none of which the model supports
- Inputs above 131,072 tokens
- Sensitive data on the free tier, which Google's pricing page marks as used to improve its products

## Benchmarks

- Artificial Analysis Speech to Speech Index (High): 82.6 (https://artificialanalysis.ai/speech-to-speech)
- Big Bench Audio (vendor-reported): 97.7% (https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/)
- τ-Voice (vendor-reported): 68.6% (https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/)
- Sierra τ-Voice-banking (vendor-reported): 35.1% (https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/)

## Sources

- [Google AI for Developers: Gemini API pricing](https://ai.google.dev/gemini-api/docs/pricing)
- [Google: Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking (Sep 15, 2026, updated Sep 17)](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/)
- [Gemini API model page: gemini-3.8-live-extended-thinking](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live-extended-thinking)
- [Artificial Analysis: Speech to Speech Index leaderboard](https://artificialanalysis.ai/speech-to-speech)

Canonical: https://neomanex.com/models/gemini-3-8-live-extended-thinking