Model comparison
Compare Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking using the same provider-sourced voice & realtime rubric. No mystery score and no invented benchmark ranking.
Quick take
Google's real-time voice model for responsive conversations with audio, text and visual context.
Audio input and output are charged separately, not as one flat call-minute price. Text, visual context, thinking and search can add to the bill.
A separate Gemini voice model that works through complex requests in the background while keeping the conversation going.
Integration differs from standard Live: tools must be asynchronous, and the app must track interaction_status. A finished utterance does not mean the background task has finished.
Compare the published facts
Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.
| Voice & realtime | Gemini 3.8 Live | Gemini 3.8 Live Extended Thinking |
|---|---|---|
| Price basisToken-, character-, or minute-based price for the listed access route. | Audio $0.005/min in · $0.018/min out | Audio $0.005/min in · $0.018/min out |
| Interaction modeSpeech-to-speech, audio-to-audio, or streamed text-to-speech behavior. | Speech-to-speech with visual input and interleaved reasoning | Speech-to-speech with visual input and background reasoning |
| Published latencyProvider-published measurement with its stated exclusions; not a Cody test. | Not published | Not published |
| LanguagesProvider-documented language coverage or a clear unpublished marker. | 97 languages (Google launch claim) | Multilingual; verify current Live API support |
| Tools & controlNative function calling, reasoning, or speech-control features. | Functions (async by default), search grounding | Async functions only, search grounding |
| Context or input limitDocumented token or character limit where it is meaningful. | 131,072 input · 65,536 output | 131,072 input · 65,536 output |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
Google says paid Gemini API prompts and responses are not used to improve its products. Unpaid-service content generally may be used, with different treatment for EEA, UK, and Swiss users; check the current terms for your account and region.
Provider and API links
Google says paid Gemini API prompts and responses are not used to improve its products. Unpaid-service content generally may be used, with different treatment for EEA, UK, and Swiss users; check the current terms for your account and region.
Provider and API links
Frequently asked questions
Gemini 3.8 Live: Google's real-time voice model for responsive conversations with audio, text and visual context. Gemini 3.8 Live Extended Thinking: A separate Gemini voice model that works through complex requests in the background while keeping the conversation going.
Consider Gemini 3.8 Live when your priority is Conversational customer support. Consider Gemini 3.8 Live Extended Thinking when your priority is Multi-step voice support workflows. Test both with your own data and provider route before committing.
No. This comparison aligns provider-published facts for the Voice & realtime category. It does not claim a universal winner or combine incompatible third-party benchmark scores.
