All models
Voice & realtimeLive
GoogleGemini 3.8 Live Extended Thinking
A separate Gemini voice model that works through complex requests in the background while keeping the conversation going.
Plain-English overview
What Gemini 3.8 Live Extended Thinking actually is
Extended Thinking combines live speech with background planning and tool use. It can give spoken progress updates while working through a multi-step request, with low, medium or high thinking levels.
Its input and output limits match Gemini 3.8 Live. Google lists the same token rates for both, but extra reasoning can increase usage. GPT-Live 1 instead delegates deeper work to a separately chosen backend agent.
Good fit for
- Multi-step voice support workflows
- Spoken planning and research assistants
- Agents that explain progress during tool calls
Category comparison
The facts that matter for voice models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Price basis
- Audio $0.005/min in · $0.018/min outToken-, character-, or minute-based price for the listed access route.
- Interaction mode
- Speech-to-speech with visual input and background reasoningSpeech-to-speech, audio-to-audio, or streamed text-to-speech behavior.
- Published latency
- Not publishedProvider-published measurement with its stated exclusions; not a Cody test.
- Languages
- Multilingual; verify current Live API supportProvider-documented language coverage or a clear unpublished marker.
- Tools & control
- Async functions only, search groundingNative function calling, reasoning, or speech-control features.
- Context or input limit
- 131,072 input · 65,536 outputDocumented token or character limit where it is meaningful.
API and provider access
Where to get Gemini 3.8 Live Extended Thinking
Availability
Regions and access stage
Available through the Gemini Live API and Google AI Studio in supported regions.
Use Google's live available-regions list and verify feature restrictions for the selected route.
Check live availabilityData and training
The route matters.
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.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Gemini 3.8 Live Extended Thinking FAQ
What is Gemini 3.8 Live Extended Thinking?
A separate Gemini voice model that works through complex requests in the background while keeping the conversation going. Extended Thinking combines live speech with background planning and tool use. It can give spoken progress updates while working through a multi-step request, with low, medium or high thinking levels.
When was Gemini 3.8 Live Extended Thinking released?
Gemini 3.8 Live Extended Thinking was released on September 15, 2026 according to the cited provider materials.
Where can I access Gemini 3.8 Live Extended Thinking?
Available through the Gemini Live API and Google AI Studio in supported regions. The access routes listed in this guide are Google.
How much does Gemini 3.8 Live Extended Thinking cost?
$0.005/min audio input · $0.018/min audio output. Paid-tier rates: $3 audio input and $12 audio output per million tokens. Text is $0.75 input and $4.50 output; image/video input is $1 per million tokens. Thinking and paid search usage can add cost.
Where is Gemini 3.8 Live Extended Thinking available?
Available through the Gemini Live API and Google AI Studio in supported regions. Use Google's live available-regions list and verify feature restrictions for the selected route.
Is my Gemini 3.8 Live Extended Thinking API data used for training?
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. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
Head-to-head comparisons
Gemini 3.8 Live Extended Thinking vs GPT-Live 1
OpenAI's full-duplex voice frontend for natural conversation that delegates deeper reasoning and actions to a separate backend agent.
Open full comparisonGemini 3.8 Live Extended Thinking vs Gemini 3.8 Live
Google's real-time voice model for responsive conversations with audio, text and visual context.
Open full comparisonGemini 3.8 Live Extended Thinking vs GPT-Realtime-2.1
OpenAI's realtime speech-to-speech reasoning model for tool-using voice agents that also need text and image context.
Open full comparisonGemini 3.8 Live Extended Thinking vs Gemini 3.1 Flash Live Preview
Google's preview audio-to-audio model for low-latency dialogue with multimodal awareness, thinking, search grounding, and function calling.
Open full comparisonGemini 3.8 Live Extended Thinking vs Eleven v3 Conversational
ElevenLabs' expressive realtime text-to-speech model for natural dialogue, emotional delivery, audio tags, and more than 70 languages.
Open full comparisonGemini 3.8 Live Extended Thinking vs Inworld Realtime TTS-2
Inworld's newest expressive realtime text-to-speech model, designed to remember conversational delivery and speak in more than 100 languages.
Open full comparisonGemini 3.8 Live Extended Thinking vs Grok Voice Think Fast 2.0
SpaceXAI's current realtime speech-to-speech model for sub-second conversational agents with tool access.
Open full comparison
