{"slug": "gemini-3-8-live-extended-thinking-audio-to-audio", "title": "Gemini 3.8 Live Extended Thinking audio-to-audio", "summary": "Google released Gemini 3.8 Live Extended Thinking, an audio-to-audio model that performs background reasoning and asynchronous tool calls while streaming continuous audio, with a 131,072-token input limit and 65,536-token output limit. The model, updated September 2026, requires clients to keep listening after turnComplete: true and to track the interaction_status field (IN_PROGRESS or IDLE), and it supports only asynchronous non-blocking function calling. Background reasoning is configured via thinking_config with thinking_level set to low, medium, or high; MINIMAL is not supported.", "body_md": "Gemini 3.8 Live Extended Thinking is our high-reasoning audio-to-audio model recommended when higher background reasoning is required for complex, multi-step problem solving during real-time voice interactions. It processes background reasoning and asynchronous tool calls while streaming continuous audio responses.\n\n## Documentation\n\nVisit the [Live API](https://ai.google.dev/gemini-api/docs/live-api) guide for full coverage\nof features and capabilities.\n\n## gemini-3.8-live-extended-thinking\n\n| Property | Description | \n|---|---|\n| Model code | `gemini-3.8-live-extended-thinking` | \n| Supported data types | **Inputs** Text, images, audio, video **Output** Text and audio | \n| Token limits <sup>[\\[*\\]](https://ai.google.dev/gemini-api/docs/tokens)</sup> | **Input token limit** 131,072 **Output token limit** 65,536 | \n| Capabilities | Supported Not supported Not supported Not supported Supported (Async only) Not supported Not supported Supported Supported Not supported Supported Not supported | \n| Consumption options | Not supported | \n| Versions | [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. | \n| Latest update | September 2026 | \n| Model card | [Model card](https://deepmind.google/models/model-cards/gemini-3-8-audio/) | \n\n## Upgrading to Gemini 3.8 Live Extended Thinking\n\nGemini 3.8 Live Extended Thinking introduces background reasoning during live audio sessions. When integrating this model, update your client state management to handle asynchronous reasoning signals:\n\n- **Asynchronous reasoning protocol** : When interacting with models that use\nasynchronous reasoning,`turnComplete: true` no longer indicates that the\nmodel is idle. The server may continue processing background reasoning or\ntool calls. Your client must continue listening for subsequent server\nmessages (such as tool calls or audio frames) after`turnComplete: true` arrives.\n- **Monitoring `interaction_status`** : Use the` interaction_status` field on\nincoming server messages to determine current server state:\n  - `IN_PROGRESS` : The server is actively processing user input, running\nbackground reasoning, or awaiting responses for asynchronous tool calls.\nAdditional model output or tool calls may follow.\n  - `IDLE` : The server has finished all processing, reasoning, and tool calls.\nThe session is idle and waiting for user input.\n- **Asynchronous function calling** : Only asynchronous non-blocking execution\n(`behavior: NON_BLOCKING` ) is supported. Synchronous blocking mode is not\nsupported and returns a hard error. Function scheduling configurations are not\nsupported.\n- **Thinking configuration** : Configure background reasoning using`thinking_config` in your setup configuration (`thinking_level` :`low` ,`medium` , or`high` ). Note that`MINIMAL` is not supported.\n- **Client content updates** :`send_client_content` is supported throughout\nthe entire session lifecycle with explicit roles (`user` or`model` ).\nSetting`turn_complete=true` immediately interrupts active generation.\n- **Proactive audio** : Permanently enabled. Setting`proactive_audio: false` returns an error.\n\nFor a feature comparison across all Live API models, see the\n[Model comparison](https://ai.google.dev/gemini-api/docs/live-api/capabilities#model-comparison)\ntable.", "url": "https://wpnews.pro/news/gemini-3-8-live-extended-thinking-audio-to-audio", "canonical_source": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live-extended-thinking", "published_at": "2026-09-15 17:11:58+00:00", "updated_at": "2026-09-15 17:20:48.835071+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-agents", "natural-language-processing"], "entities": ["Google", "Gemini 3.8 Live Extended Thinking", "Live API", "DeepMind"], "alternates": {"html": "https://wpnews.pro/news/gemini-3-8-live-extended-thinking-audio-to-audio", "markdown": "https://wpnews.pro/news/gemini-3-8-live-extended-thinking-audio-to-audio.md", "text": "https://wpnews.pro/news/gemini-3-8-live-extended-thinking-audio-to-audio.txt", "jsonld": "https://wpnews.pro/news/gemini-3-8-live-extended-thinking-audio-to-audio.jsonld"}}