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

# Supported Models

> Guide to using different chat models with Browsernode

## Overview

Here's how to configure the models.

### Migration from Langchain

with `import { ChatOpenAI } from "browsernode";` or `import { ChatOpenAI } from "browsernode/llm";`  etc. The methods should be compatible(ish).

We also made and example [here](https://github.com/leoning60/browsernode/blob/main/examples/models/langchain) to help you stay with Langchain in case your workflow requires it.

## Model Recommendations

We recommend using GPT-4.1 for the best performance (best accuracy \~\$0.01 per step). The best price to performance can be achieved using `gemini-2.5-flash` (currently also the most popular model, costs \~\$0.001 per step).

## Supported Models

Our library natively supports the following models:

* OpenAI
* Anthropic
* Azure OpenAI
* Gemini

We also support all other models that can be called via OpenAI compatible API (deepseek, novita, x, qwen). Please open a PR if you want to add a model.

We have natively switched to structured output when possible,

### OpenAI

OpenAI's GPT-4.1 models are recommended for best performance.

```js theme={null}
import { Agent } from "browsernode";
import { ChatOpenAI } from "browsernode/llm";

// Initialize the model
const llm = new ChatOpenAI({
	model: "gpt-4.1",
	apiKey: process.env.OPENAI_API_KEY,
});
// Create agent with the model
const agent = new Agent({
    task: task,
    llm: llm,
});
```

Required environment variables:

```bash .env theme={null}
OPENAI_API_KEY=
```

### Anthropic

```js theme={null}
import { Agent } from "browsernode";
import { ChatAnthropic } from "browsernode/llm";

// Initialize the model
const llm = new ChatAnthropic({
	model: "claude-3-5-sonnet-20240620",
	apiKey: process.env.ANTHROPIC_API_KEY,
});

// Create agent with the model
const agent = new Agent({
    task: task,
    llm: llm,
});
```

And add the variable:

```bash .env theme={null}
ANTHROPIC_API_KEY=
```

### Azure OpenAI

```js theme={null}
import { Agent } from "browsernode";
import { ChatAzureOpenAI } from "browsernode/llm";

// Initialize the model
const llm = new ChatAzureOpenAI({
	model: "gpt-4.1",
	apiKey: process.env.AZURE_OPENAI_API_KEY,
	endpoint: process.env.AZURE_OPENAI_ENDPOINT,
});

// Create agent with the model
const agent = new Agent({
    task: task,
    llm: llm,
});
```

Required environment variables:

```bash .env theme={null}
AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com/
AZURE_OPENAI_API_KEY=
```

### Gemini

> \[!IMPORTANT] `GEMINI_API_KEY` was the old environment var name, it should be called `GOOGLE_API_KEY` as of 2025-05.

```js theme={null}
import { Agent } from "browsernode";
import { ChatGoogle } from "browsernode/llm";

// Initialize the model
const llm = new ChatGoogle({
	model: "gemini-2.5-flash",
	apiKey: process.env.GOOGLE_API_KEY,
});

// Create agent with the model
const agent = new Agent({
    task: task,
    llm: llm,
});
```

Required environment variables:

```bash .env theme={null}
GOOGLE_API_KEY=
```