> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-opensw-1774858546-a100bff.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

Deep Agents work with any [LangChain chat model](/oss/javascript/langchain/models) that supports [tool calling](/oss/javascript/langchain/models#tool-calling).

## Pass a model string

The simplest way to specify a model is to pass a string to [`createDeepAgent`](https://reference.langchain.com/javascript/deepagents/agent/createDeepAgent). Use the `provider:model` format to select a specific provider:

```typescript theme={null}
const agent = createDeepAgent({ model: "openai:gpt-5.3-codex" });
```

Under the hood, this calls [`init_chat_model`](https://reference.langchain.com/javascript/langchain/chat_models/universal/initChatModel) with default parameters.

## Configure model parameters

To configure model-specific parameters, use [`init_chat_model`](https://reference.langchain.com/javascript/langchain/chat_models/universal/initChatModel) or instantiate a provider model class directly:

<CodeGroup>
  ```typescript initChatModel theme={null}
  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={null}
  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>
  Available parameters vary by provider. See the [chat model integrations](/oss/javascript/integrations/chat) page for provider-specific configuration options.
</Note>

## Select a model at runtime

If your application lets users choose a model (for example using a dropdown in the UI), use [middleware](/oss/javascript/langchain/middleware) to swap the model at runtime without rebuilding the agent.

Pass the user's model selection through [runtime context](/oss/javascript/langchain/agents#dynamic-model), then use a `wrap_model_call` middleware to override the model on each invocation using the @\[`@wrap_model_call`] decorator:

```typescript theme={null}
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,
});

// Invoke with the user's model selection
const result = await agent.invoke(
  { messages: [{ role: "user", content: "Hello!" }] },
  { context: { model: "openai:gpt-4.1" } },
);
```

<Tip>
  For more dynamic model patterns (foe example routing based on conversation complexity or cost optimization), see [Dynamic model](/oss/javascript/langchain/agents#dynamic-model) in the LangChain agents guide.
</Tip>

## Supported models

Deep Agents work with any chat model that supports [tool calling](/oss/javascript/langchain/models#tool-calling). See [chat model integrations](/oss/javascript/integrations/chat) for the full list of supported providers.

### Suggested models

These models perform well on the [Deep Agents eval suite](https://github.com/langchain-ai/deepagents/tree/main/libs/deepagents/tests/evals), which tests basic agent operations. Passing these evals is necessary but not sufficient for strong performance on longer, more complex tasks.

| Provider                                                      | Models                                                                                                                                   |
| ------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| [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`                                                                                       |
| Open-weight                                                   | `GLM-5`, `Kimi-K2.5`, `MiniMax-M2.5`, `qwen3.5-397B-A17B`, `devstral-2-123B`                                                             |

Open-weight models are available through providers like [OpenRouter](/oss/javascript/integrations/chat/openrouter), [Fireworks](/oss/javascript/integrations/chat/fireworks) or [Ollama](/oss/javascript/integrations/chat/ollama).

## Learn more

* [Models in LangChain](/oss/javascript/langchain/models): chat model features including tool calling, structured output, and multimodality

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/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>