Gemini 3.8 Live

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.

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. Documentation Visit the Live API https://ai.google.dev/gemini-api/docs/live-api guide for full coverage of features and capabilities. gemini-3.8-live | Property | Description | |---|---| | Model code | gemini-3.8-live | | Supported data types | Inputs Text, images, audio, video Output Text and audio | | Token limits <sup \ \ https://ai.google.dev/gemini-api/docs/tokens </sup | Input token limit 131,072 Output token limit 65,536 | | Capabilities | Supported Not supported Not supported Not supported Supported Not supported Not supported Supported Supported Not supported Supported interleaved reasoning Not supported | | Consumption options | Not supported | | Versions | model version patterns https://ai.google.dev/gemini-api/docs/models/gemini model-versions for more details. | | Latest update | September 2026 | | Model card | Model card https://deepmind.google/models/model-cards/gemini-3-8-audio/ | Migrating from Gemini 3.1 Flash Live Gemini 3.8 Live delivers ultra-low latency audio-to-audio interactions and expands support for asynchronous workflows. When migrating from gemini-3.1-flash-live-preview , review the following updates: - Model string : Update your model string from gemini-3.1-flash-live-preview to gemini-3.8-live . - Thinking level : thinking level is not supported for gemini-3.8-live . Omit thinking level or thinking config from your session setup. - Asynchronous function calling : Async execution behavior: NON BLOCKING is now the default function calling mode. You can still use synchronous blocking mode for backwards compatibility by setting behavior: BLOCKING on your tool declarations. Function scheduling SILENT , WHEN IDLE , INTERRUPTED is supported. - Client content updates : send client content is supported throughout the entire session lifecycle with explicit roles user or model . Setting turn complete=true unconditionally interrupts active model generation. If you send content without turn complete , the server waits for subsequent messages before responding. - Proactive audio : Proactive audio is now permanently enabled. Setting proactive audio: false returns an error. - Affective dialogue : Affective dialogue is removed from the API. Remove any enable affective dialog configurations from your code. - Turn coverage : Defaults to TURN INCLUDES AUDIO ACTIVITY AND ALL VIDEO . Video frames are sent to the model by default, so only send frames when needed to manage context and cost. - Response modalities : Audio is the supported response modality. Enable output audio transcription if your application requires a text transcript. For a feature comparison across all Live API models, see the Model comparison https://ai.google.dev/gemini-api/docs/live-api/capabilities model-comparison table.