Gemini 3.8 Live
Google · Veröffentlicht Sept. 2026
Gemini 3.8 Live is Google's default Live API model for low-latency voice agents that keep talking while tool calls finish in the background. Conditional because Google bills Gemini 3.8 Live Extended Thinking at the identical rate, and Artificial Analysis scores that sibling higher on its Speech to Speech Index, so you pay the same for less reasoning. Pick 3.8 Live only when turn latency matters more than reasoning depth: developers shipping real-time voice experiences on the Gemini API.
Ist es das Richtige für dich?
Gut für
- Voice agents where turn latency is the priority, per Google's "without reasoning-induced delays" positioning
- Keeping a conversation going while tools and API calls finish in the background
Nicht geeignet für
- Multi-step reasoning mid-call, where Google recommends the Extended Thinking model
- Workloads that need structured outputs, context caching, code execution or the Batch API, none of which the model supports
- Sensitive data on the free tier, which Google's pricing page marks as used to improve its products
Leistung nach Aufgabe
Low-latency voice conversation
Google's default Live model for low-latency voice without reasoning-induced delays
Complex reasoning during calls
Google recommends the Extended Thinking model when higher background reasoning is required
Preise
Eingabe
$0.75 / 1M (text)
Ausgabe
$4.50 / 1M (text)
Kontext
131K in, 65K out; audio $3/$12 per 1M
Benchmarks
| Benchmark | Wert | Quelle |
|---|---|---|
| Artificial Analysis Speech to Speech Index | 76.0 | Quelle |
Noch keine Urteilsänderungen
Die Uhr läuft ab dem ersten Tag. Änderungen erscheinen hier, sobald sich unser Urteil weiterentwickelt.
Quellen
- Gemini API pricing (Live Extended Thinking: $0.75/$4.50 text, $3/$12 audio)Okt. 2026
- Google: Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking (Sep 15, 2026, updated Sep 17)Okt. 2026
- Gemini API model page: gemini-3.8-liveSept. 2026
- Gemini API model page: gemini-3.8-live-extended-thinkingSept. 2026
- Artificial Analysis: Speech-to-Speech leaderboard (Grok Voice 3.0 86.9, 0.81 s)Okt. 2026
Prüfprotokoll
- Preise· Keine Änderungen
Automatisierter Agent
- Preise· Keine Änderungen
Automatisierter Agent
- Preise· Keine Änderungen
Automatisierter Agent