> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# 模型

Deep Agents 可与任何支持[工具调用](/oss/javascript/langchain/models#tool-calling)的 [LangChain 聊天模型](/oss/javascript/langchain/models) 协同工作。

## 传入模型字符串

指定模型的最简单方式是向 [`createDeepAgent`](https://reference.langchain.com/javascript/deepagents/agent/createDeepAgent) 传入一个字符串。使用 `provider:model` 格式来选择特定的提供商：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const agent = createDeepAgent({ model: "openai:gpt-5.3-codex" });
```

在底层，这会使用默认参数调用 [`init_chat_model`](https://reference.langchain.com/javascript/langchain/chat_models/universal/initChatModel)。

## 配置模型参数

要配置模型特定的参数，请使用 [`init_chat_model`](https://reference.langchain.com/javascript/langchain/chat_models/universal/initChatModel) 或直接实例化提供商模型类：

<CodeGroup>
  ```typescript initChatModel theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  import { initChatModel } from "langchain/chat_models/universal";
  import { createDeepAgent } from "deepagents";

  const model = await initChatModel("anthropic:claude-sonnet-4-6", {
      maxTokens: 16000,
      thinking: { type: "enabled", budgetTokens: 10000 },  // [!code highlight]
  });
  const agent = createDeepAgent({ model });
  ```

  ```typescript Provider package theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  import { ChatAnthropic } from "@langchain/anthropic";
  import { createDeepAgent } from "deepagents";

  const model = new ChatAnthropic({
      model: "claude-sonnet-4-6",
      maxTokens: 16000,
      thinking: { type: "enabled", budgetTokens: 10000 },  // [!code highlight]
  });
  const agent = createDeepAgent({ model });
  ```
</CodeGroup>

<Note>
  可用参数因提供商而异。有关提供商特定的配置选项，请参阅[聊天模型集成](/oss/javascript/integrations/chat)页面。
</Note>

## 在运行时选择模型

如果你的应用程序允许用户选择模型（例如通过 UI 中的下拉菜单），可以使用[中间件](/oss/javascript/langchain/middleware)在运行时切换模型，而无需重新构建智能体。

通过[运行时上下文](/oss/javascript/langchain/agents#dynamic-model)传递用户的模型选择，然后使用 `wrap_model_call` 中间件，通过 @\[`@wrap_model_call`] 装饰器在每次调用时覆盖模型：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { initChatModel, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const contextSchema = z.object({
  model: z.string(),
});

const configurableModel = createMiddleware({
  name: "ConfigurableModel",
  wrapModelCall: async (request, handler) => {
    const modelName = request.runtime.context.model;
    const model = await initChatModel(modelName);
    return handler({ ...request, model });
  },
});

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-4-6",
  middleware: [configurableModel],
  contextSchema,
});

// 使用用户选择的模型进行调用
const result = await agent.invoke(
  { messages: [{ role: "user", content: "Hello!" }] },
  { context: { model: "openai:gpt-4.1" } },
);
```

<Tip>
  关于更多动态模型模式（例如基于对话复杂性或成本优化的路由），请参阅 LangChain 智能体指南中的[动态模型](/oss/javascript/langchain/agents#dynamic-model)。
</Tip>

## 支持的模型

Deep Agents 可与任何支持[工具调用](/oss/javascript/langchain/models#tool-calling)的聊天模型协同工作。有关支持的提供商的完整列表，请参阅[聊天模型集成](/oss/javascript/integrations/chat)。

### 推荐模型

这些模型在 [Deep Agents 评估套件](https://github.com/langchain-ai/deepagents/tree/main/libs/deepagents/tests/evals) 上表现良好，该套件测试基本的智能体操作。通过这些评估是必要的，但对于在更长、更复杂的任务上获得强大性能来说还不够充分。

| 提供商                                                           | 模型                                                                                                                                       |
| ------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| [Anthropic](/oss/javascript/integrations/providers/anthropic) | `claude-opus-4-6`, `claude-opus-4-5`, `claude-sonnet-4-6`, `claude-sonnet-4`, `claude-sonnet-4-5`, `claude-haiku-4-5`, `claude-opus-4-1` |
| [OpenAI](/oss/javascript/integrations/providers/openai)       | `gpt-5.4`, `gpt-4o`, `gpt-4.1`, `o4-mini`, `gpt-5.2-codex`, `gpt-4o-mini`, `o3`                                                          |
| [Google](/oss/javascript/integrations/providers/google)       | `gemini-3-flash-preview`, `gemini-3.1-pro-preview`                                                                                       |
| 开源权重模型                                                        | `GLM-5`, `Kimi-K2.5`, `MiniMax-M2.5`, `qwen3.5-397B-A17B`, `devstral-2-123B`                                                             |

开源权重模型可通过 [OpenRouter](/oss/javascript/integrations/chat/openrouter)、[Fireworks](/oss/javascript/integrations/chat/fireworks) 或 [Ollama](/oss/javascript/integrations/chat/ollama) 等提供商获取。

## 了解更多

* [LangChain 中的模型](/oss/javascript/langchain/models)：聊天模型功能，包括工具调用、结构化输出和多模态

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\deepagents\models.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>