{"slug": "gemini-3-8-live", "title": "Gemini 3.8 Live", "summary": "Google released Gemini 3.8 Live, a model code `gemini-3.8-live` designed as the default option for low-latency voice agent experiences and real-time dialogue, with an input token limit of 131,072 and an output token limit of 65,536. The model, updated in September 2026, supports interleaved reasoning, asynchronous function calling, full session client content updates, and built-in audio streaming, and replaces `gemini-3.1-flash-live-preview` for developers migrating from that version. Google said `thinking_level` is no longer supported, proactive audio is permanently enabled, affective dialogue is removed, and asynchronous function calling with `behavior: NON_BLOCKING` is now the default mode.", "body_md": "Gemini 3.8 Live is the default option for most low-latency voice agent experiences and real-time dialogue without reasoning-induced delays. It supports interleaved reasoning, asynchronous function calling, full session client content updates, and built-in audio streaming.\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\n\n| Property | Description | \n|---|---|\n| Model code | `gemini-3.8-live` | \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 Not supported Not supported Supported Supported Not supported Supported (interleaved reasoning) 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## Migrating from Gemini 3.1 Flash Live\n\nGemini 3.8 Live delivers ultra-low latency audio-to-audio interactions\nand expands support for asynchronous workflows. When migrating from\n`gemini-3.1-flash-live-preview`, review the following updates:\n\n- **Model string** : Update your model string from`gemini-3.1-flash-live-preview` to`gemini-3.8-live` .\n- **Thinking level** :`thinking_level` is not supported for`gemini-3.8-live` .\nOmit`thinking_level` (or`thinking_config` ) from your session setup.\n- **Asynchronous function calling** : Async execution (`behavior: NON_BLOCKING` )\nis now the default function calling mode. You can still use synchronous\nblocking mode for backwards compatibility by setting`behavior: BLOCKING` on\nyour tool declarations. Function scheduling (`SILENT` ,`WHEN_IDLE` ,`INTERRUPTED` ) is supported.\n- **Client content updates** :`send_client_content` is supported throughout the\nentire session lifecycle with explicit roles (`user` or`model` ). Setting`turn_complete=true` unconditionally interrupts active model generation. If\nyou send content without`turn_complete` , the server waits for subsequent\nmessages before responding.\n- **Proactive audio** : Proactive audio is now permanently enabled. Setting`proactive_audio: false` returns an error.\n- **Affective dialogue** : Affective dialogue is removed from the API. Remove\nany`enable_affective_dialog` configurations from your code.\n- **Turn coverage** : Defaults to`TURN_INCLUDES_AUDIO_ACTIVITY_AND_ALL_VIDEO` . Video frames are sent to the\nmodel by default, so only send frames when needed to manage context and cost.\n- **Response modalities** : Audio is the supported response modality. Enable\noutput audio transcription if your application requires a text transcript.\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", "canonical_source": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live", "published_at": "2026-09-16 01:52:01+00:00", "updated_at": "2026-09-16 02:07:31.715860+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-agents", "natural-language-processing"], "entities": ["Google", "Gemini 3.8 Live", "gemini-3.8-live", "Gemini 3.1 Flash Live", "gemini-3.1-flash-live-preview", "Live API", "DeepMind"], "alternates": {"html": "https://wpnews.pro/news/gemini-3-8-live", "markdown": "https://wpnews.pro/news/gemini-3-8-live.md", "text": "https://wpnews.pro/news/gemini-3-8-live.txt", "jsonld": "https://wpnews.pro/news/gemini-3-8-live.jsonld"}}