> ## 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.

# qwen4-max (Latest Model)

> Qwen4-Max is the next-generation flagship multimodal model in the Qwen family, combining text generation, image and video understanding, and deep reasoning. It is designed for coding, office productivity, frontend design, and complex agentic tasks. With support for web search, tool calling, and structured outputs, along with compatibility with the OpenAI and Anthropic APIs, it enables developers to build intelligent applications capable of multimodal understanding and task execution.

<meta property="og:title" content="Qwen4-Max" />

Model invocation ID (`model` parameter): `qwen4-max`

## Inference provider

Alibaba Cloud Model Studio

## Model capabilities

<Tabs>
  <Tab title="China (Beijing)">
    Deployment scope: Chinese mainland

    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Input modalities</p></td><td style={{ verticalAlign: "top" }}><p>Text, image, video</p></td><td style={{ verticalAlign: "top" }}><p>Output modality</p></td><td style={{ verticalAlign: "top" }}><p>Text</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Streaming</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>deep thinking</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>parallel tool calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>web search</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>prefix completion</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Function Calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Thinking summary and encryption</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>OpenAI Chat Completions, Responses, Anthropic Messages, DashScope</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Structured output (JSON Object, JSON Schema)</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Explicit cache, implicit cache</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Batch inference</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>fine-tuning</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>model deployment</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p /></td><td style={{ verticalAlign: "top" }}><p /></td></tr></tbody></table>
  </Tab>

  <Tab title="Singapore">
    Scope: International

    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Input modalities</p></td><td style={{ verticalAlign: "top" }}><p>Text, image, video</p></td><td style={{ verticalAlign: "top" }}><p>Output modality</p></td><td style={{ verticalAlign: "top" }}><p>Text</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Streaming</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>deep thinking</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>parallel tool calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>web search</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>prefix completion</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Function Calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Thinking summary and encryption</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>OpenAI Chat Completions, Responses, Anthropic Messages, DashScope</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Structured output (JSON Object, JSON Schema)</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Explicit cache, implicit cache</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Batch inference</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p>fine-tuning</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>model deployment</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p /></td><td style={{ verticalAlign: "top" }}><p /></td></tr></tbody></table>
  </Tab>

  <Tab title="Germany (Frankfurt)">
    Scope: Global

    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Input modalities</p></td><td style={{ verticalAlign: "top" }}><p>Text, image, video</p></td><td style={{ verticalAlign: "top" }}><p>Output modality</p></td><td style={{ verticalAlign: "top" }}><p>Text</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Streaming</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>deep thinking</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>parallel tool calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>web search</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>prefix completion</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Function Calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Thinking summary and encryption</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>OpenAI Chat Completions, Responses, Anthropic Messages, DashScope</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Structured output (JSON Object, JSON Schema)</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Explicit cache, implicit cache</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Batch inference</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p>fine-tuning</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>model deployment</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p /></td><td style={{ verticalAlign: "top" }}><p /></td></tr></tbody></table>
  </Tab>

  <Tab title="US (Virginia)">
    Scope: Global

    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Input modalities</p></td><td style={{ verticalAlign: "top" }}><p>Text, image, video</p></td><td style={{ verticalAlign: "top" }}><p>Output modality</p></td><td style={{ verticalAlign: "top" }}><p>Text</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Streaming</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>deep thinking</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>parallel tool calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>web search</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>prefix completion</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Function Calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Thinking summary and encryption</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>OpenAI Chat Completions, Responses, Anthropic Messages, DashScope</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Structured output (JSON Object, JSON Schema)</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Explicit cache, implicit cache</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Batch inference</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p>fine-tuning</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>model deployment</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p /></td><td style={{ verticalAlign: "top" }}><p /></td></tr></tbody></table>
  </Tab>

  <Tab title="Japan (Tokyo)">
    Scope: Global

    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Input modalities</p></td><td style={{ verticalAlign: "top" }}><p>Text, image, video</p></td><td style={{ verticalAlign: "top" }}><p>Output modality</p></td><td style={{ verticalAlign: "top" }}><p>Text</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Streaming</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>deep thinking</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>parallel tool calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>web search</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>prefix completion</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Function Calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Thinking summary and encryption</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>OpenAI Chat Completions, Responses, Anthropic Messages, DashScope</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Structured output (JSON Object, JSON Schema)</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Explicit cache, implicit cache</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Batch inference</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p>fine-tuning</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>model deployment</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p /></td><td style={{ verticalAlign: "top" }}><p /></td></tr></tbody></table>
  </Tab>

  <Tab title="Hong Kong (China)">
    Scope: Global

    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th><th style={{ verticalAlign: "top" }}><p>Capability</p></th><th style={{ verticalAlign: "top" }}><p>Support</p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Input modalities</p></td><td style={{ verticalAlign: "top" }}><p>Text, image, video</p></td><td style={{ verticalAlign: "top" }}><p>Output modality</p></td><td style={{ verticalAlign: "top" }}><p>Text</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Streaming</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>deep thinking</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>parallel tool calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>web search</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>prefix completion</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Function Calling</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Thinking summary and encryption</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>OpenAI Chat Completions, Responses, Anthropic Messages, DashScope</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Structured output (JSON Object, JSON Schema)</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td><td style={{ verticalAlign: "top" }}><p>Explicit cache, implicit cache</p></td><td style={{ verticalAlign: "top" }}><p>Supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Batch inference</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p>fine-tuning</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>model deployment</p></td><td style={{ verticalAlign: "top" }}><p>Not supported</p></td><td style={{ verticalAlign: "top" }}><p /></td><td style={{ verticalAlign: "top" }}><p /></td></tr></tbody></table>
  </Tab>
</Tabs>

## Model rate limits and context

<table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /><col style={{ width: "25%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}><p>Parameter</p></th><th style={{ verticalAlign: "top" }}><p>Token</p></th><th style={{ verticalAlign: "top" }}><p>Parameter</p></th><th style={{ verticalAlign: "top" }}><p>Token</p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>Maximum input length</p></td><td style={{ verticalAlign: "top" }}><p>991,808</p></td><td style={{ verticalAlign: "top" }}><p>Maximum output length</p></td><td style={{ verticalAlign: "top" }}><p>131,072</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Maximum input length (thinking mode)</p></td><td style={{ verticalAlign: "top" }}><p>983,616</p></td><td style={{ verticalAlign: "top" }}><p>Maximum output length (thinking mode)</p></td><td style={{ verticalAlign: "top" }}><p>262,144</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>Context length</p></td><td style={{ verticalAlign: "top" }}><p>1,000,000</p></td><td style={{ verticalAlign: "top" }}><p>Maximum chain-of-thought length</p></td><td style={{ verticalAlign: "top" }}><p>262,144</p></td></tr></tbody></table>

## Default parameters

<table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "40%" }} /><col style={{ width: "60%" }} /></colgroup><thead><tr><th style={{ verticalAlign: "top" }}><p>Parameter</p></th><th style={{ verticalAlign: "top" }}><p>Default</p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p>temperature</p></td><td style={{ verticalAlign: "top" }}><p>1.0 in thinking mode; 0.7 in non-thinking mode.</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>top\_p</p></td><td style={{ verticalAlign: "top" }}><p>0.95 in thinking mode; 0.8 in non-thinking mode.</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>top\_k</p></td><td style={{ verticalAlign: "top" }}><p>20</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>repetition\_penalty</p></td><td style={{ verticalAlign: "top" }}><p>1.0</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>presence\_penalty</p></td><td style={{ verticalAlign: "top" }}><p>0.0 (Thinking); 1.5 (Non-thinking)</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>logprobs</p></td><td style={{ verticalAlign: "top" }}><p>false</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>enable\_thinking</p></td><td style={{ verticalAlign: "top" }}><p>true</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>preserve\_thinking</p></td><td style={{ verticalAlign: "top" }}><p>true</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>reasoning\_effort</p></td><td style={{ verticalAlign: "top" }}><p>high</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>thinking\_budget</p></td><td style={{ verticalAlign: "top" }}><p>131072</p></td></tr><tr><td style={{ verticalAlign: "top" }}><p>max\_completion\_tokens</p></td><td style={{ verticalAlign: "top" }}><p>262144 (Thinking); 131072 (Non-thinking)</p></td></tr></tbody></table>

When `reasoning_effort` and `thinking_budget` are omitted, the defaults are `reasoning_effort=high` and `thinking_budget=131072`.

## Thinking effort

| Protocol                            | Parameter              | Supported values       | Default | Mapping                                               |
| ----------------------------------- | ---------------------- | ---------------------- | ------- | ----------------------------------------------------- |
| OpenAI Chat Completions / DashScope | `reasoning_effort`     | `low`, `high`, `xhigh` | `high`  | `minimal` → `low`; `medium` → `high`; `max` → `xhigh` |
| OpenAI Responses                    | `reasoning.effort`     | `low`, `high`, `xhigh` | `high`  | `minimal` → `low`; `medium` → `high`; `max` → `xhigh` |
| Anthropic Messages                  | `output_config.effort` | `low`, `high`, `xhigh` | `high`  | `medium` → `high`; `max` → `xhigh`                    |

## Model pricing

<Tabs>
  <Tab title="Singapore">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "14.285714%" }} />

        <col style={{ width: "14.285714%" }} />

        <col style={{ width: "14.285714%" }} />

        <col style={{ width: "14.285714%" }} />

        <col style={{ width: "14.285714%" }} />

        <col style={{ width: "14.285714%" }} />

        <col style={{ width: "14.285714%" }} />
      </colgroup>

      <thead>
        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Model ID</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Deployment scope</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Mode</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input tokens per request</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input price (per 1 million tokens)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Output price (per 1 million tokens)</strong>

            > <strong>Chain of thought + answer</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Free quota</strong>[(Note)](/en/model-studio/new-free-quota#591f3dfedfyzj)

            <sup>Valid for 90 days from the date of Model Studio activation, model release, or application approval, whichever is later</sup>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max

            > [Cache price (per million tokens)](/en/model-studio/explicit-cache-qwen4#billing)
          </td>

          <td style={{ verticalAlign: "top" }}>
            International
          </td>

          <td style={{ verticalAlign: "top" }}>
            Non-Thinking and Thinking modes
          </td>

          <td style={{ verticalAlign: "top" }}>
            0\<Token≤1M
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$1.5
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$4.5
          </td>

          <td style={{ verticalAlign: "top" }}>
            1 million tokens
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>

  <Tab title="China (Beijing)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "20%" }} />

        <col style={{ width: "20%" }} />

        <col style={{ width: "20%" }} />

        <col style={{ width: "20%" }} />

        <col style={{ width: "20%" }} />
      </colgroup>

      <thead>
        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Model ID</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Mode</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input tokens per request</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input price (per 1 million tokens)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Output price (per 1 million tokens)</strong>

            > <strong>Chain of thought + answer</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max

            > [Cache price (per million tokens)](/en/model-studio/explicit-cache-qwen4#billing)
          </td>

          <td style={{ verticalAlign: "top" }}>
            Non-Thinking and Thinking modes
          </td>

          <td style={{ verticalAlign: "top" }}>
            0\<Token≤1M
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$1.413
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$4.24
          </td>
        </tr>
      </tbody>
    </table>

    **qwen4-max — Batch price (per million tokens)**

| API                                                                                | Input                   | Output                 |
| ---------------------------------------------------------------------------------- | ----------------------- | ---------------------- |
| [Batch File](/en/model-studio/batch-interfaces-compatible-with-openai)             | \$0.707                 | \$2.12                 |
| [Batch Chat](/en/model-studio/openai-compatible-batch-chat) (limited-time 50% off) | Original price: \$1.413 | Original price: \$4.24 |
  </Tab>

  <Tab title="Hong Kong (China)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.75%" }} />
      </colgroup>

      <thead>
        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Model ID</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Deployment scope</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Mode</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input tokens per request</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input price (per 1 million tokens)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Output price (per 1 million tokens)</strong>

            > <strong>Chain of thought + answer</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max

            > [Cache price (per million tokens)](/en/model-studio/explicit-cache-qwen4#billing)
          </td>

          <td style={{ verticalAlign: "top" }}>
            Global
          </td>

          <td style={{ verticalAlign: "top" }}>
            Non-Thinking and Thinking modes
          </td>

          <td style={{ verticalAlign: "top" }}>
            0\<Token≤1M
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$1.413
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$4.24
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>

  <Tab title="Germany (Frankfurt)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.75%" }} />
      </colgroup>

      <thead>
        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Model ID</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Deployment scope</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Mode</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input tokens per request</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input price (per 1 million tokens)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Output price (per 1 million tokens)</strong>

            > <strong>Chain of thought + answer</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max

            > [Cache price (per million tokens)](/en/model-studio/explicit-cache-qwen4#billing)
          </td>

          <td style={{ verticalAlign: "top" }}>
            Global
          </td>

          <td style={{ verticalAlign: "top" }}>
            Non-Thinking and Thinking modes
          </td>

          <td style={{ verticalAlign: "top" }}>
            0\<Token≤1M
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$1.413
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$4.24
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>

  <Tab title="US (Virginia)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.65%" }} />

        <col style={{ width: "16.75%" }} />
      </colgroup>

      <thead>
        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Model ID</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Deployment scope</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Mode</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input tokens per request</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input price (per 1 million tokens)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Output price (per 1 million tokens)</strong>

            > <strong>Chain of thought + answer</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max

            > [Cache price (per million tokens)](/en/model-studio/explicit-cache-qwen4#billing)
          </td>

          <td style={{ verticalAlign: "top" }}>
            Global
          </td>

          <td style={{ verticalAlign: "top" }}>
            Non-Thinking and Thinking modes
          </td>

          <td style={{ verticalAlign: "top" }}>
            0\<Token≤1M
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$1.413
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$4.24
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>

  <Tab title="Japan (Tokyo)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "16.73%" }} />

        <col style={{ width: "16.73%" }} />

        <col style={{ width: "16.73%" }} />

        <col style={{ width: "16.73%" }} />

        <col style={{ width: "16.73%" }} />

        <col style={{ width: "16.35%" }} />
      </colgroup>

      <thead>
        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Model ID</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Deployment scope</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Mode</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input tokens per request</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Input price (per 1 million tokens)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Output price (per 1 million tokens)</strong>

            > <strong>Chain of thought + answer</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max

            > [Cache price (per million tokens)](/en/model-studio/explicit-cache-qwen4#billing)
          </td>

          <td style={{ verticalAlign: "top" }}>
            Global
          </td>

          <td style={{ verticalAlign: "top" }}>
            Non-Thinking and Thinking modes
          </td>

          <td style={{ verticalAlign: "top" }}>
            0\<Token≤1M
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$1.413
          </td>

          <td style={{ verticalAlign: "top" }}>
            \$4.24
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>
</Tabs>

For prices and free quotas, see [Model pricing](/en/model-studio/model-pricing).

## Rate limits

<Tabs>
  <Tab title="Singapore">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25.00%" }} /><col style={{ width: "25.00%" }} /><col style={{ width: "25.00%" }} /><col style={{ width: "25.00%" }} /></colgroup><thead style={{ verticalAlign: "top" }}><tr><th style={{ verticalAlign: "top" }}><p><strong>Bailian platform monthly consumption:</strong></p></th><th style={{ verticalAlign: "top" }}><p><strong>Tier 1 (current) ≤\$8,000</strong></p></th><th style={{ verticalAlign: "top" }}><p><strong>Tier 2 \$8,000\~\$140,000</strong></p></th><th style={{ verticalAlign: "top" }}><p><strong>Tier 3 >\$140,000</strong></p></th></tr><tr><th style={{ verticalAlign: "top" }}><p><strong>Supported models</strong></p></th><th colSpan={3} style={{ verticalAlign: "top" }}><p><strong>TPM rate limit tiers</strong></p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p><strong>qwen4-max</strong></p></td><td style={{ verticalAlign: "top" }}><p>5,000,000</p></td><td style={{ verticalAlign: "top" }}><p>10,000,000</p></td><td style={{ verticalAlign: "top" }}><p>20,000,000</p></td></tr></tbody></table>
  </Tab>

  <Tab title="China (Beijing)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}><colgroup><col style={{ width: "25.00%" }} /><col style={{ width: "25.00%" }} /><col style={{ width: "25.00%" }} /><col style={{ width: "25.00%" }} /></colgroup><thead style={{ verticalAlign: "top" }}><tr><th style={{ verticalAlign: "top" }}><p><strong>Bailian platform monthly consumption:</strong></p></th><th style={{ verticalAlign: "top" }}><p><strong>Tier 1 (current) ≤\$8,000</strong></p></th><th style={{ verticalAlign: "top" }}><p><strong>Tier 2 \$8,000\~\$140,000</strong></p></th><th style={{ verticalAlign: "top" }}><p><strong>Tier 3 >\$140,000</strong></p></th></tr><tr><th style={{ verticalAlign: "top" }}><p><strong>Supported models</strong></p></th><th colSpan={3} style={{ verticalAlign: "top" }}><p><strong>TPM rate limit tiers</strong></p></th></tr></thead><tbody><tr><td style={{ verticalAlign: "top" }}><p><strong>qwen4-max</strong></p></td><td style={{ verticalAlign: "top" }}><p>5,000,000</p></td><td style={{ verticalAlign: "top" }}><p>10,000,000</p></td><td style={{ verticalAlign: "top" }}><p>20,000,000</p></td></tr></tbody></table>
  </Tab>

  <Tab title="US (Virginia)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "35%" }} />

        <col style={{ width: "15%" }} />

        <col style={{ width: "25%" }} />

        <col style={{ width: "25%" }} />
      </colgroup>

      <thead>
        <tr>
          <th rowSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Model</strong>
          </th>

          <th rowSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Service Deployment Scope</strong>
          </th>

          <th colSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Rate limit conditions (triggered when any value is exceeded)</strong>

            > <strong>The following are per-minute rate limit conditions. The service may impose limits based on RPS (RPM/60) and TPS (TPM/60).</strong>
          </th>
        </tr>

        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Calls per minute (RPM)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Tokens consumed per minute (TPM)</strong>

            > <strong>Includes input and output tokens</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max
          </td>

          <td style={{ verticalAlign: "top" }}>
            Global
          </td>

          <td style={{ verticalAlign: "top" }}>
            30,000
          </td>

          <td style={{ verticalAlign: "top" }}>
            5,000,000
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>

  <Tab title="Germany (Frankfurt)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "35%" }} />

        <col style={{ width: "15%" }} />

        <col style={{ width: "25%" }} />

        <col style={{ width: "25%" }} />
      </colgroup>

      <thead>
        <tr>
          <th rowSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Model</strong>
          </th>

          <th rowSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Service Deployment Scope</strong>
          </th>

          <th colSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Rate limiting conditions (triggered when any value is exceeded)</strong>

            > <strong>The following are per-minute rate limiting conditions. The service may also limit by RPS (RPM/60) and TPS (TPM/60)</strong>
          </th>
        </tr>

        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Calls per minute (RPM)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Tokens consumed per minute (TPM)</strong>

            > <strong>Includes input and Output tokens</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max
          </td>

          <td style={{ verticalAlign: "top" }}>
            Global
          </td>

          <td style={{ verticalAlign: "top" }}>
            30,000
          </td>

          <td style={{ verticalAlign: "top" }}>
            5,000,000
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>

  <Tab title="Hong Kong (China)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "35%" }} />

        <col style={{ width: "15%" }} />

        <col style={{ width: "25%" }} />

        <col style={{ width: "25%" }} />
      </colgroup>

      <thead>
        <tr>
          <th rowSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Model</strong>
          </th>

          <th rowSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Service Deployment Scope</strong>
          </th>

          <th colSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Rate limiting conditions (triggered when any value is exceeded)</strong>

            > <strong>The following are per-minute rate limiting conditions. The service may limit by RPS (RPM/60) and TPS (TPM/60).</strong>
          </th>
        </tr>

        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Calls per minute (RPM)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Tokens consumed per minute (TPM)</strong>

            > <strong>Includes input and output Tokens</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max
          </td>

          <td style={{ verticalAlign: "top" }}>
            Global
          </td>

          <td style={{ verticalAlign: "top" }}>
            30,000
          </td>

          <td style={{ verticalAlign: "top" }}>
            5,000,000
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>

  <Tab title="Japan (Tokyo)">
    <table style={{ display: "table", tableLayout: "fixed", width: "100%", overflowWrap: "anywhere" }}>
      <colgroup>
        <col style={{ width: "35%" }} />

        <col style={{ width: "15%" }} />

        <col style={{ width: "25%" }} />

        <col style={{ width: "25%" }} />
      </colgroup>

      <thead>
        <tr>
          <th rowSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Model</strong>
          </th>

          <th rowSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Service Deployment Scope</strong>
          </th>

          <th colSpan={2} style={{ verticalAlign: "top" }}>
            <strong>Rate limit conditions (triggered when any value is exceeded)</strong>

            > <strong>The following are per-minute rate limit conditions. The service may limit by RPS (RPM/60) and TPS (TPM/60).</strong>
          </th>
        </tr>

        <tr>
          <th style={{ verticalAlign: "top" }}>
            <strong>Calls per minute (RPM)</strong>
          </th>

          <th style={{ verticalAlign: "top" }}>
            <strong>Tokens consumed per minute (TPM)</strong>

            > <strong>Includes input and output Tokens</strong>
          </th>
        </tr>
      </thead>

      <tbody>
        <tr>
          <td style={{ verticalAlign: "top" }}>
            qwen4-max
          </td>

          <td style={{ verticalAlign: "top" }}>
            Global
          </td>

          <td style={{ verticalAlign: "top" }}>
            30,000
          </td>

          <td style={{ verticalAlign: "top" }}>
            5,000,000
          </td>
        </tr>
      </tbody>
    </table>
  </Tab>
</Tabs>

For rate limits and AutoTPM tiers, see [Rate limits](/en/model-studio/rate-limit).

## API access

- [OpenAI Chat Completions](/en/model-studio/qwen-api-via-openai-chat-completions)
- [OpenAI Responses](/en/model-studio/qwen-api-via-openai-responses)
- [Anthropic Messages](/en/model-studio/anthropic-api-messages)
- [DashScope](/en/model-studio/qwen-api-via-dashscope)
- [Model capabilities](/en/model-studio/text-generation-model)
- [CoT Summary](/en/model-studio/cot-summary)
- [Prompt Cache](/en/model-studio/explicit-cache-qwen4)

## Usage

### Explicit caching

Reuse common input prefixes such as system prompts, tool descriptions, and reference documents to reduce repeated input costs. Supported by OpenAI Chat Completions, Responses, and Anthropic Messages, with TTLs of `5m` and `1h`. See [Explicit caching](/en/model-studio/explicit-cache-qwen4).

### Chain-of-thought summary and encryption

Returns a reasoning summary for display and encrypted reasoning for use in subsequent turns. Pass historical encrypted content back unchanged in multi-turn conversations. For configuration, streaming responses, and complete examples, see [Chain-of-thought summary and encryption](/en/model-studio/cot-summary).
