> ## AI Agent Context
> - Full documentation index: https://aistudio.google.com/llms.txt
> - Gemini Docs MCP server (consistent live info): https://gemini-api-docs-mcp.dev
> - Coding agent skills & setup guide: https://aistudio.google.com/docs/coding-agents.md

# Gemini 3.8 Live Extended Thinking

Gemini 3.8 Live Extended Thinking (`gemini-3.8-live-extended-thinking`) is our
high-reasoning audio-to-audio Live API model for complex, multi-step problem
solving during real-time voice interactions. It processes configurable
background reasoning (`low`, `medium`, `high`), thought summaries, and
asynchronous tool calls while streaming continuous audio responses.

For low-latency conversational voice experiences without background reasoning
delays, see [Gemini 3.8 Live](/docs/models/gemini-3.8-live).

{% button href="https://aistudio.google.com/live?model=gemini-3.8-live-extended-thinking" variant="ais" %} Try in Google AI Studio {% /button %}

## Documentation  {% id="documentation" %}

Visit the [Live API](/docs/live-api) and
[Thinking in the Live API](/docs/live-api/thinking) guides for full coverage of
reasoning configurations and asynchronous tool integrations.

## gemini-3.8-live-extended-thinking  {% id="gemini-38-live-extended-thinking" %}

{% table variant="model" %}
  * Property
  * Description

  ---

  *     {% section class="model-property" %}
  {% icon name="id_card" /%}Model code

    {% /section %}

  * `gemini-3.8-live-extended-thinking`

  ---

  *     {% section class="model-property" %}
  {% icon name="save" /%}Supported data types

    {% /section %}

  *     **Inputs** Text, images, audio

    **Output** Text and audio


  ---

  *     {% section class="model-property" %}
  {% icon name="token_auto" /%}Token limits{% sup %}[[*]](/docs/tokens){% /sup %}

    {% /section %}

  *     **Input token limit** 131,072

    **Output token limit** 65,536


  ---

  *     {% section class="model-property" %}
  {% icon name="handyman" /%}Capabilities

    {% /section %}

  *     {% section class="three-column-grid" %}
  {% section %}
  [**Audio generation**](/docs/speech-generation)

  {% badge type="supported" /%}

  {% /section %}

  {% section %}
  [**Code execution**](/docs/code-execution)

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  [**Context caching**](/docs/caching)

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  [**File search**](/docs/file-search)

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  [**Function calling**](/docs/function-calling)

  {% badge label=Supported (Async only) type="supported" /%}

  {% /section %}

  {% section %}
  [**Grounding with Google Maps**](/docs/maps-grounding)

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  [**Grounding with Google Search**](/docs/google-search)

  {% badge type="supported" /%}

  {% /section %}

  {% section %}
  [**Image generation**](/docs/image-generation)

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  [**Live API**](/docs/live-api)

  {% badge type="supported" /%}

  {% /section %}

  {% section %}
  [**Structured outputs**](/docs/structured-output)

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  [**Thinking**](/docs/thinking)

  {% badge type="supported" /%}

  {% /section %}

  {% section %}
  [**URL context**](/docs/url-context)

  {% badge type="not-supported" /%}

  {% /section %}

    {% /section %}


  ---

  *     {% section class="model-property" %}
  {% icon name="speed" /%}Consumption options

    {% /section %}

  *     {% section class="three-column-grid" %}
  {% section %}
  [**Batch API**](/docs/batch-api)

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  [**Flex inference**](/docs/flex-inference)

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  [**Priority inference**](/docs/priority-inference)

  {% badge type="not-supported" /%}

  {% /section %}

    {% /section %}


  ---

  *     {% section class="model-property" %}
  {% icon name="123" /%}Versions

    {% /section %}

  *     Read the [model version patterns](/docs/models#model-versions) for more details.

    *     Stable: `gemini-3.8-live-extended-thinking`


  ---

  *     {% section class="model-property" %}
  {% icon name="calendar_month" /%}Latest update

    {% /section %}

  * September 2026

  ---

  *     {% section class="model-property" %}
  {% icon name="id_card" /%}Model card

    {% /section %}

  * [Model card](https://deepmind.google/models/model-cards/gemini-3-8-audio/)

  ---

  *     {% section class="model-property" %}
  {% icon name="paid" /%}Pricing

    {% /section %}

  * [Pricing](/docs/pricing#gemini-3.8-live)
{% /table %}

## Upgrading to Gemini 3.8 Live Extended Thinking  {% id="upgrading" %}

Gemini 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:

*   **Asynchronous reasoning protocol**: When interacting with models that use
    asynchronous reasoning, `turnComplete: true` no longer signals that the
    model is completely idle. The server may continue processing background
    reasoning or tool calls. Keep your client listening for subsequent server
    messages (such as tool calls or audio frames) after `turnComplete: true`
    arrives.
*   **Monitoring `interaction_status`**: Check `server_content.interaction_status`
    on incoming
    [`BidiGenerateContentServerContent`](/api-reference/live#BidiGenerateContentServerContent)
    messages to determine the current server state before closing the session:
    *   `IN_PROGRESS`: The server is actively processing user input, running
        background reasoning, or awaiting responses for asynchronous tool calls.
        Additional model output or tool calls may follow.
    *   `IDLE`: The server has finished all processing, reasoning, and tool
        calls. The session is idle and waiting for user input.

*   **Function calling**: Function calling is exclusively asynchronous
    (`behavior: NON_BLOCKING`). Synchronous blocking mode returns an error, and
    function scheduling options (`SILENT`, `WHEN_IDLE`, and `INTERRUPTED`) are
    not supported. See
    [Asynchronous function calling](/docs/live-api/tools#async-function-calling).
*   **Thinking configuration**: Configure background reasoning using
    `thinking_config` in your session setup with `thinking_level` values `low`,
    `medium`, or `high`. Note that `MINIMAL` is not supported. See
    [Thinking in the Live API](/docs/live-api/thinking).
*   **Client content updates**: `send_client_content` is supported throughout
    the entire session lifecycle (both initial history seeding and mid-turn
    context updates) with explicit roles (`user` or `model`). Setting
    `turn_complete=true` immediately interrupts active generation. See
    [Incremental content updates](/docs/live-api/capabilities#incremental-updates).
*   **Proactive audio**: Permanently enabled. Setting `proactive_audio: false`
    returns an error.
*   **Affective dialogue**: Removed from the API. Remove any
    `enable_affective_dialog` configurations from your setup.

For a feature comparison across all Live API models, see the
[Model comparison](/docs/live-api/capabilities#model-comparison) table in the
capabilities guide.

