# Text generation

> Choose the right text generation model for AI agents, chatbots, and document processing.

## Recommended models for coding tools <span id="oc1a2b3c4d5e02" /> <span id="oc1a2b3c4d5e01" />

We recommend `qwen3.7-plus` for balanced performance and cost, with full tool calling and a 1M-token context window for large codebases. For the strongest reasoning, choose `qwen3.8-max`.

## Migrate from closed-source models <span id="mg1a2b3c4d5e02" /> <span id="mg1a2b3c4d5e01" />

Map your current GPT, Claude, or Gemini model to an equivalent Bailian model.

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}><colgroup><col style={{ width: "18.125%" }} /><col style={{ width: "45%" }} /><col style={{ width: "36.875%" }} /></colgroup><thead><tr><th /><th><p><strong>Closed-source examples</strong></p></th><th><p><strong>Bailian recommendation</strong></p></th></tr></thead><tbody><tr><td><p>Highest capability</p></td><td><p>GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro</p></td><td><p><code>qwen3.8-max</code></p></td></tr><tr><td><p>Balanced</p></td><td><p>GPT-5.4, Claude Sonnet 4.6, Gemini 3 Pro</p></td><td><p><code>qwen3.7-plus</code>, <code>deepseek-v4-pro</code>, <code>glm-5.2</code></p></td></tr><tr><td><p>Lightweight & low-cost</p></td><td><p>GPT-5.4-mini, Claude Haiku 4.5, Gemini 3.1 Flash</p></td><td><p><code>qwen3.8-flash</code>, <code>deepseek-v4-flash</code>, <code>MiniMax-M2.5</code></p></td></tr></tbody></table>

## Use cases <span id="t1a2b3c4d5e6f8" /> <span id="t1a2b3c4d5e6f7" />

Start with `qwen3.7-plus` for chatbots, content generation, summarization, and document processing — it balances performance, cost, and built-in tools with a 1M-token context window. To cut costs, switch to `qwen3.8-flash` , which offers similar capabilities at a lower price. For the strongest reasoning, use `qwen3.8-max`.

### Office productivity (non-coding) <span id="h3-office-productivity" /> <span id="office-productivity-non-coding" />

For non-coding office tasks such as document drafting, email composition, meeting note summarization, and data analytics, start with `qwen3.7-plus` — it balances performance and cost with a 1M-token context window, Function Calling support, and built-in tools. To reduce costs, try `qwen3.8-flash` , which delivers near-flagship performance at a lower price with the same context length. For the strongest reasoning capability, choose `qwen3.8-max`. For long-document processing such as reviewing multiple contracts, use `qwen-long` (10M-token context window).

<Note>
  TONGYI Lingma and Qoder are AI coding tools designed for software development. They are not intended for general office productivity tasks.
</Note>

### Context window <span id="t1a2b3c4d5e701" /> <span id="t1a2b3c4d5e700" />

1 million tokens is roughly 750,000 English words, or 8-10 novels.

- For long documents or large codebases: `qwen3.8-max` / `qwen3.8-flash` / `qwen3.7-plus` / `qwen3.7-flash` (1 million tokens).
- For standard tasks: 128k-256k tokens is typically sufficient.

For context window details, visit the Models page.

[China (Beijing)](https://modelstudio.console.alibabacloud.com/cn-beijing/model/market) | [Singapore](https://modelstudio.console.alibabacloud.com/ap-southeast-1/model/market) | [US](https://modelstudio.console.alibabacloud.com/us-east-1/model/market) | [China (Hong Kong)](https://modelstudio.console.alibabacloud.com/cn-hongkong/model/market) | [Frankfurt](https://modelstudio.console.alibabacloud.com/eu-central-1/model/market)

### Thinking mode <span id="t1a2b3c4d5e709" /> <span id="t1a2b3c4d5e708" />

Step-by-step reasoning for multi-step math, code debugging, architecture planning, and legal cross-referencing.

Enable with the `enable_thinking` parameter, or use `reasoning`.`effort` in the Responses API to control thinking depth. All Qwen3+ models support this feature, most of which operate in a hybrid mode togglable per request.

> See [Deep thinking](/help/en/model-studio/deep-thinking).

### Function calling and built-in tools <span id="t1a2b3c4d5e713" /> <span id="t1a2b3c4d5e712" />

Let the model take actions such as querying weather, searching databases, or booking meetings.

- Function calling (custom tools that the model calls): Supported by all general-purpose models.
- Built-in tools (web search, code interpreter, web scraping) with no configuration required.

> See [Tool calling](/help/en/model-studio/tool-calls).

### Structured output <span id="t1a2b3c4d5e721" /> <span id="t1a2b3c4d5e720" />

Forces valid JSON output, useful for extracting structured data like names and addresses from text.

> See [Structured output](/help/en/model-studio/qwen-structured-output).

### Batch inference <span id="t1a2b3c4d5e725" /> <span id="t1a2b3c4d5e724" />

Process large volumes at lower cost when latency is not critical.

> See [Batch inference](/help/en/model-studio/batch-inference).

## Recommended models <span id="t1a2b3c4d5e729" /> <span id="t1a2b3c4d5e728" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}><colgroup><col style={{ width: "27.576792%" }} /><col style={{ width: "11.467577%" }} /><col style={{ width: "13.788396%" }} /><col style={{ width: "17.269625%" }} /><col style={{ width: "14.948805%" }} /><col style={{ width: "14.948805%" }} /></colgroup><thead><tr><th><p><strong>Model ID</strong></p></th><th><p><strong>Context</strong></p></th><th><p><strong>Thinking mode</strong></p></th><th><p><strong>Function Calling</strong></p></th><th><p><strong>Built-in tools</strong></p></th><th><p><strong>Structured output</strong></p></th></tr></thead><tbody><tr><td><p><code>qwen3.8-max</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.8-max-0902</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.8-flash</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.7-plus</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.7-flash</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>kimi-k2.6</code></p></td><td><p>256k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-v4-pro</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>deepseek-v4-flash</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>glm-5.2</code></p></td><td><p>198k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>MiniMax-M2.5</code></p></td><td><p>192k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr></tbody></table>

## Legacy models <span id="t1a2b3c4d5e801" /> <span id="t1a2b3c4d5e800" />

The following models are legacy and no longer recommended. Visit the Models page to view detailed model parameters, such as context window and billing.

### Qwen3.7 <span id="3d7f167281kx4" /> <span id="0b0739f2bbtlt" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}>
  <colgroup>
    <col style={{ width: "27.576792%" }} />

    <col style={{ width: "11.467577%" }} />

    <col style={{ width: "13.788396%" }} />

    <col style={{ width: "17.269625%" }} />

    <col style={{ width: "14.948805%" }} />

    <col style={{ width: "14.948805%" }} />
  </colgroup>

  <thead>
    <tr>
      <th>
        <strong>Model ID</strong>
      </th>

      <th>
        <strong>Context</strong>
      </th>

      <th>
        <strong>Thinking mode</strong>
      </th>

      <th>
        <strong>Function Calling</strong>
      </th>

      <th>
        <strong>Built-in tools</strong>
      </th>

      <th>
        <strong>Structured output</strong>
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        `qwen3.7-max`

        <Accordion title="View snapshots">
          `qwen3.7-max-preview` `qwen3.7-max-2026-06-08` `qwen3.7-max-2026-05-20` `qwen3.7-max-2026-05-17`
        </Accordion>
      </td>

      <td>
        1M
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>
    </tr>
  </tbody>
</table>

#### Qwen3.6 <span id="t1a2b3c4d5e803" /> <span id="t1a2b3c4d5e802" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}>
  <colgroup>
    <col style={{ width: "27.576792%" }} />

    <col style={{ width: "11.467577%" }} />

    <col style={{ width: "13.788396%" }} />

    <col style={{ width: "17.269625%" }} />

    <col style={{ width: "14.948805%" }} />

    <col style={{ width: "14.948805%" }} />
  </colgroup>

  <thead>
    <tr>
      <th>
        <strong>Model ID</strong>
      </th>

      <th>
        <strong>Context</strong>
      </th>

      <th>
        <strong>Thinking mode</strong>
      </th>

      <th>
        <strong>Function Calling</strong>
      </th>

      <th>
        <strong>Built-in tools</strong>
      </th>

      <th>
        <strong>Structured output</strong>
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        `qwen3.6-max-preview`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3.6-plus`
      </td>

      <td>
        1M
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3.6-flash`

        <Accordion title="View snapshots">
          `qwen3.6-flash-2026-04-16`
        </Accordion>
      </td>

      <td>
        1M
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>
    </tr>
  </tbody>
</table>

#### Qwen3.5 <span id="t1a2b3c4d5e861" /> <span id="t1a2b3c4d5e860" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}><colgroup><col style={{ width: "27.576792%" }} /><col style={{ width: "11.467577%" }} /><col style={{ width: "13.788396%" }} /><col style={{ width: "17.269625%" }} /><col style={{ width: "14.948805%" }} /><col style={{ width: "14.948805%" }} /></colgroup><thead><tr><th><p><strong>Model ID</strong></p></th><th><p><strong>Context</strong></p></th><th><p><strong>Thinking mode</strong></p></th><th><p><strong>Function Calling</strong></p></th><th><p><strong>Built-in tools</strong></p></th><th><p><strong>Structured output</strong></p></th></tr></thead><tbody><tr><td><p><code>qwen3.5-plus</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.5-flash</code></p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.5-397b-a17b</code></p></td><td><p>256k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.5-122b-a10b</code></p></td><td><p>256k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.5-27b</code></p></td><td><p>256k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen3.5-35b-a3b</code></p></td><td><p>256k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr></tbody></table>

#### Qwen3 <span id="lgcy011" /> <span id="lgcy010" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}>
  <colgroup>
    <col style={{ width: "27.576792%" }} />

    <col style={{ width: "11.467577%" }} />

    <col style={{ width: "13.788396%" }} />

    <col style={{ width: "17.269625%" }} />

    <col style={{ width: "14.948805%" }} />

    <col style={{ width: "14.948805%" }} />
  </colgroup>

  <thead>
    <tr>
      <th>
        <strong>Model ID</strong>
      </th>

      <th>
        <strong>Context</strong>
      </th>

      <th>
        <strong>Thinking mode</strong>
      </th>

      <th>
        <strong>Function Calling</strong>
      </th>

      <th>
        <strong>Built-in tools</strong>
      </th>

      <th>
        <strong>Structured output</strong>
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        `qwen3-max`

        <Accordion title="View snapshots">
          `qwen3-max-2026-01-23` `qwen3-max-preview` `qwen3-max-2025-09-23`
        </Accordion>
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-235b-a22b`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-235b-a22b-thinking-2507`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Unsupported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-235b-a22b-instruct-2507`
      </td>

      <td>
        256k
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-next-80b-a3b-thinking`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Unsupported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-next-80b-a3b-instruct`
      </td>

      <td>
        256k
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-32b`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-30b-a3b`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-30b-a3b-thinking-2507`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Unsupported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-30b-a3b-instruct-2507`
      </td>

      <td>
        256k
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-14b`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-8b`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-4b`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-1.7b`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-0.6b`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>
  </tbody>
</table>

#### Qwen3-Coder <span id="lgcy101" /> <span id="lgcy100" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}>
  <colgroup>
    <col style={{ width: "27.576792%" }} />

    <col style={{ width: "11.467577%" }} />

    <col style={{ width: "13.788396%" }} />

    <col style={{ width: "17.269625%" }} />

    <col style={{ width: "14.948805%" }} />

    <col style={{ width: "14.948805%" }} />
  </colgroup>

  <thead>
    <tr>
      <th>
        <strong>Model ID</strong>
      </th>

      <th>
        <strong>Context</strong>
      </th>

      <th>
        <strong>Thinking mode</strong>
      </th>

      <th>
        <strong>Function Calling</strong>
      </th>

      <th>
        <strong>Built-in tools</strong>
      </th>

      <th>
        <strong>Structured output</strong>
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        `qwen3-coder-plus`

        <Accordion title="View snapshots">
          `qwen3-coder-plus-2025-09-23` `qwen3-coder-plus-2025-07-22`
        </Accordion>
      </td>

      <td>
        1M
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-coder-flash`

        <Accordion title="View snapshots">
          `qwen3-coder-flash-2025-07-28`
        </Accordion>
      </td>

      <td>
        1M
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-coder-next`
      </td>

      <td>
        256k
      </td>

      <td>
        Supported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-coder-480b-a35b-instruct`
      </td>

      <td>
        256k
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen3-coder-30b-a3b-instruct`
      </td>

      <td>
        256k
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>
  </tbody>
</table>

#### Qwen2.5 (open source) <span id="lgcy201" /> <span id="lgcy200" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}><colgroup><col style={{ width: "27.576792%" }} /><col style={{ width: "11.467577%" }} /><col style={{ width: "13.788396%" }} /><col style={{ width: "17.269625%" }} /><col style={{ width: "14.948805%" }} /><col style={{ width: "14.948805%" }} /></colgroup><thead><tr><th><p><strong>Model ID</strong></p></th><th><p><strong>Context</strong></p></th><th><p><strong>Thinking mode</strong></p></th><th><p><strong>Function Calling</strong></p></th><th><p><strong>Built-in tools</strong></p></th><th><p><strong>Structured output</strong></p></th></tr></thead><tbody><tr><td><p><code>qwen2.5-omni-7b</code></p></td><td><p>32k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen2.5-vl-72b-instruct</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen2.5-vl-32b-instruct</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen2.5-vl-7b-instruct</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen2.5-vl-3b-instruct</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen2.5-72b-instruct</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen2.5-32b-instruct</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen2.5-14b-instruct</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen2.5-14b-instruct-1m</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen2.5-7b-instruct</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen2.5-7b-instruct-1m</code></p></td><td><p>1M</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr></tbody></table>

#### Translation <span id="lgcy401" /> <span id="lgcy400" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}><colgroup><col style={{ width: "27.576792%" }} /><col style={{ width: "11.467577%" }} /><col style={{ width: "13.788396%" }} /><col style={{ width: "17.269625%" }} /><col style={{ width: "14.948805%" }} /><col style={{ width: "14.948805%" }} /></colgroup><thead><tr><th><p><strong>Model ID</strong></p></th><th><p><strong>Context</strong></p></th><th><p><strong>Thinking mode</strong></p></th><th><p><strong>Function Calling</strong></p></th><th><p><strong>Built-in tools</strong></p></th><th><p><strong>Structured output</strong></p></th></tr></thead><tbody><tr><td><p><code>qwen-mt-plus</code></p></td><td><p>16k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen-mt-turbo</code></p></td><td><p>16k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen-mt-flash</code></p></td><td><p>16k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen-mt-lite</code></p></td><td><p>16k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr></tbody></table>

#### Qwen-Long <span id="lgcy501" /> <span id="lgcy500" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}>
  <colgroup>
    <col style={{ width: "27.576792%" }} />

    <col style={{ width: "11.467577%" }} />

    <col style={{ width: "13.788396%" }} />

    <col style={{ width: "17.269625%" }} />

    <col style={{ width: "14.948805%" }} />

    <col style={{ width: "14.948805%" }} />
  </colgroup>

  <thead>
    <tr>
      <th>
        <strong>Model ID</strong>
      </th>

      <th>
        <strong>Context</strong>
      </th>

      <th>
        <strong>Thinking mode</strong>
      </th>

      <th>
        <strong>Function Calling</strong>
      </th>

      <th>
        <strong>Built-in tools</strong>
      </th>

      <th>
        <strong>Structured output</strong>
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        `qwen-long`

        <Accordion title="View snapshots">
          `qwen-long-2025-01-25`
        </Accordion>
      </td>

      <td>
        10M
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>

    <tr>
      <td>
        `qwen-long-latest`
      </td>

      <td>
        10M
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Unsupported
      </td>

      <td>
        Supported
      </td>
    </tr>
  </tbody>
</table>

#### Role-playing <span id="lgcy601" /> <span id="lgcy600" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}><colgroup><col style={{ width: "27.576792%" }} /><col style={{ width: "11.467577%" }} /><col style={{ width: "13.788396%" }} /><col style={{ width: "17.269625%" }} /><col style={{ width: "14.948805%" }} /><col style={{ width: "14.948805%" }} /></colgroup><thead><tr><th><p><strong>Model ID</strong></p></th><th><p><strong>Context</strong></p></th><th><p><strong>Thinking mode</strong></p></th><th><p><strong>Function Calling</strong></p></th><th><p><strong>Built-in tools</strong></p></th><th><p><strong>Structured output</strong></p></th></tr></thead><tbody><tr><td><p><code>qwen-plus-character</code></p></td><td><p>32k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen-plus-character-ja</code></p></td><td><p>32k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen-flash-character</code></p></td><td><p>8k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr></tbody></table>

#### Legacy Qwen <span id="lgcy701" /> <span id="lgcy700" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}><colgroup><col style={{ width: "27.576792%" }} /><col style={{ width: "11.467577%" }} /><col style={{ width: "13.788396%" }} /><col style={{ width: "17.269625%" }} /><col style={{ width: "14.948805%" }} /><col style={{ width: "14.948805%" }} /></colgroup><thead><tr><th><p><strong>Model ID</strong></p></th><th><p><strong>Context</strong></p></th><th><p><strong>Thinking mode</strong></p></th><th><p><strong>Function Calling</strong></p></th><th><p><strong>Built-in tools</strong></p></th><th><p><strong>Structured output</strong></p></th></tr></thead><tbody><tr><td><p><code>qwen-plus</code> and its snapshots</p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen-max</code> and its snapshots</p></td><td><p>128k</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen-flash</code> and its snapshots</p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwen-turbo</code> and its snapshots</p></td><td><p>1M</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>qwq-plus</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qvq-max</code> and its snapshots</p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>qwen-omni-turbo</code> and its snapshots</p></td><td><p>32k</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr></tbody></table>

#### Third-party models <span id="c885247d230bw" /> <span id="3224ea96370tn" />

<table style={{ display: "table", tableLayout: "fixed", width: "100%" }}><colgroup><col style={{ width: "27.576792%" }} /><col style={{ width: "11.467577%" }} /><col style={{ width: "13.788396%" }} /><col style={{ width: "17.269625%" }} /><col style={{ width: "14.948805%" }} /><col style={{ width: "14.948805%" }} /></colgroup><thead><tr><th><p><strong>Model ID</strong></p></th><th><p><strong>Context</strong></p></th><th><p><strong>Thinking mode</strong></p></th><th><p><strong>Function Calling</strong></p></th><th><p><strong>Built-in tools</strong></p></th><th><p><strong>Structured output</strong></p></th></tr></thead><tbody><tr><td><p><code>glm-5.1</code></p></td><td><p>198k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>glm-5</code></p></td><td><p>198k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>glm-4.7</code></p></td><td><p>198k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>glm-4.5</code></p></td><td><p>198k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>glm-4.5-air</code></p></td><td><p>198k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>MiniMax-M2.7</code></p></td><td><p>200k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>MiniMax-M2.1</code></p></td><td><p>200k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>kimi-k2.5</code></p></td><td><p>256k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>kimi-k2-thinking</code></p></td><td><p>256k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td></tr><tr><td><p><code>Moonshot-Kimi-K2-Instruct</code></p></td><td><p>256k</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-v3.2</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-v3.2-exp</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-v3.1</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-v3</code></p></td><td><p>128k</p></td><td><p>Unsupported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-r1</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-r1-0528</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-r1-distill-llama-70b</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-r1-distill-qwen-32b</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-r1-distill-qwen-14b</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-r1-distill-qwen-7b</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-r1-distill-qwen-1.5b</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr><tr><td><p><code>deepseek-r1-distill-llama-8b</code></p></td><td><p>128k</p></td><td><p>Supported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td><td><p>Unsupported</p></td></tr></tbody></table>