> ## Documentation Index
> Fetch the complete documentation index at: https://docs.modelstudio.console.alibabacloud.com/llms.txt
> Use this file to discover all available pages before exploring further.

# qwen3.8-omni-flash-realtime

> A model for real-time audio and video interaction with text and audio output, multichannel audio, and tool calling.

## Inference service provider

The inference service provider for `qwen3.8-omni-flash-realtime` is Alibaba Cloud Model Studio.

## Model capabilities

Supported regions: China (Beijing) and Singapore. Use an [API key](/en/model-studio/get-api-key) from the selected region.

| Capability         | Support                                                                                                          | Capability        | Support                                                                                                                       |
| ------------------ | ---------------------------------------------------------------------------------------------------------------- | ----------------- | ----------------------------------------------------------------------------------------------------------------------------- |
| Input modalities   | Text, streaming audio, and video (consecutive image frames)                                                      | Output modalities | Text and audio                                                                                                                |
| Function Calling   | Supports [custom tool calling](/en/model-studio/qwen-function-calling)                                           | MCP               | Supports remote MCP tools. See the [MCP interaction flow](/en/model-studio/omni-realtime-interaction-process#qwen38-mcp-flow) |
| Multichannel audio | WebSocket access supports 1, 2, or 4 channels; multichannel input uses 16 kHz PCM                                | Video aggregation | Configure `session.video.input.representation_compact`: the default is `none`; set it to `normal` to enable aggregation       |
| Voices             | The default is `Tina`. See [voice parameters and audio previews](/en/model-studio/omni-voice-list#qwen38-voices) |                   |                                                                                                                               |

Access the model through WebSocket, WebRTC, or AOQ. See the [real-time guide](/en/model-studio/realtime#7e1da95c25ej6) for examples and SDK configuration.

For WebSocket access, use a workspace-specific WebSocket endpoint. For configuration, see [Establish a connection](/en/model-studio/realtime#bdaa43cdd7hsd).

## Context limits

| Parameter                  | Value                                   | Parameter             | Value                                    |
| -------------------------- | --------------------------------------- | --------------------- | ---------------------------------------- |
| Maximum total input tokens | 196608                                  | Audio history         | Up to 100 turns and 600 seconds in total |
| Video history              | Up to 50 turns and 240 seconds in total | Maximum output tokens | 65536                                    |

Older history is discarded when the turn count or cumulative media duration exceeds a limit. Cumulative media duration is not the total session duration.

## Model pricing

See [Model pricing](/en/model-studio/model-pricing) for inference prices.

For speech output, `qwen3.8-omni-flash-realtime` bills both the audio and its corresponding text at their respective output rates. Qwen3.5-Omni-Realtime models bill only the audio; the corresponding text is not charged.

Free quota: 1 million tokens, available only in Singapore. Valid for 90 days from service activation, model release, or application approval, whichever is later. See [Free quota](/en/model-studio/new-free-quota#591f3dfedfyzj).

<Tabs>
  <Tab title="China (Beijing)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "48%" }} /><col style={{ width: "20%" }} /><col style={{ width: "32%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}>Billing item</th><th style={{ verticalAlign: "top" }}>Price (USD)</th><th style={{ verticalAlign: "top" }}>Unit</th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Input: audio</p></td><td style={{ verticalAlign: "top" }}><p>0.848</p></td><td style={{ verticalAlign: "top" }}><p>Per million tokens</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Output: audio</p></td><td style={{ verticalAlign: "top" }}><p>1.696</p></td><td style={{ verticalAlign: "top" }}><p>Per million tokens</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Input: text/images/video</p></td><td style={{ verticalAlign: "top" }}><p>0.212</p></td><td style={{ verticalAlign: "top" }}><p>Per million tokens</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Output: text</p></td><td style={{ verticalAlign: "top" }}><p>0.636</p></td><td style={{ verticalAlign: "top" }}><p>Per million tokens</p></td></tr></tbody></table>
  </Tab>

  <Tab title="Singapore">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "48%" }} /><col style={{ width: "20%" }} /><col style={{ width: "32%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}>Billing item</th><th style={{ verticalAlign: "top" }}>Price (USD)</th><th style={{ verticalAlign: "top" }}>Unit</th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Input: audio</p></td><td style={{ verticalAlign: "top" }}><p>0.93</p></td><td style={{ verticalAlign: "top" }}><p>Per million tokens</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Output: audio</p></td><td style={{ verticalAlign: "top" }}><p>1.87</p></td><td style={{ verticalAlign: "top" }}><p>Per million tokens</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Input: text/images/video</p></td><td style={{ verticalAlign: "top" }}><p>0.23</p></td><td style={{ verticalAlign: "top" }}><p>Per million tokens</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Output: text</p></td><td style={{ verticalAlign: "top" }}><p>0.7</p></td><td style={{ verticalAlign: "top" }}><p>Per million tokens</p></td></tr></tbody></table>
  </Tab>
</Tabs>

## Rate limits

Both Beijing and Singapore have limits of 60 RPM and 2,000,000 TPM. See [Rate limits](/en/model-studio/rate-limit) for model request limits.