Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Python ai-agentsai-toolsbrowser-agentbrowser-automationbrowser-usecdpcloud-browsercomputer-useheadless-browserllmmcpplaywrightpythonremote-browserstealth-browserweb-automationweb-scraping
improve model docs
Laith Weinbergerc1151715d358
diff --git a/skills/open-source/references/models.md b/skills/open-source/references/models.mdindex 57d313dde..ad277d76b 100644--- a/skills/open-source/references/models.md+++ b/skills/open-source/references/models.md@@ -1,26 +1,64 @@# Supported LLM Models+Browser Use natively supports 15+ LLM providers. Most providers accept any model string — check each provider's docs to see which models are available.++## Quick Reference++| Provider | Class | Env Variable |+|----------|-------|--------------|+| Browser Use Cloud | `ChatBrowserUse` | `BROWSER_USE_API_KEY` |+| OpenAI | `ChatOpenAI` | `OPENAI_API_KEY` |+| Anthropic | `ChatAnthropic` | `ANTHROPIC_API_KEY` |+| Google Gemini | `ChatGoogle` | `GOOGLE_API_KEY` |+| Azure OpenAI | `ChatAzureOpenAI` | `AZURE_OPENAI_*` |+| AWS Bedrock | `ChatAWSBedrock` | `AWS_ACCESS_KEY_ID` |+| DeepSeek | `ChatDeepSeek` | `DEEPSEEK_API_KEY` |+| Mistral | `ChatMistral` | `MISTRAL_API_KEY` |+| Groq | `ChatGroq` | `GROQ_API_KEY` |+| Cerebras | `ChatCerebras` | `CEREBRAS_API_KEY` |+| Ollama | `ChatOllama` | — |+| OpenRouter | `ChatOpenRouter` | `OPENROUTER_API_KEY` |+| Vercel AI Gateway | `ChatVercel` | `AI_GATEWAY_API_KEY` |+| OCI (Oracle) | `ChatOCIRaw` | OCI config file |+| LiteLLM | `ChatLiteLLM` | Provider-specific |++## Recommendations by Use Case++Based on our [benchmark of real-world browser tasks](https://browser-use.com/posts/what-model-to-use):++- **Maximum performance**: Browser Use Cloud `bu-ultra` — 78% accuracy, ~14 tasks/hour+- **Best open-source + cloud LLM**: `ChatBrowserUse(model='bu-2-0')` — 63.3% accuracy, outperforms every standalone frontier model+- **Best standalone model**: `claude-opus-4-6` — 62% accuracy, excels at custom JavaScript and structured data extraction+- **Best value**: `claude-sonnet-4-6` — 59% accuracy, near-opus quality at lower cost+- **Fast + capable**: `gemini-3-1-pro` — 59.3% accuracy+## Table of Contents-- [Browser Use (Recommended)](#browser-use)-- [Google Gemini](#google-gemini)+- [Browser Use Cloud (Recommended)](#browser-use-cloud)- [OpenAI](#openai)- [Anthropic](#anthropic)+- [Google Gemini](#google-gemini)- [Azure OpenAI](#azure-openai)- [AWS Bedrock](#aws-bedrock)+- [DeepSeek](#deepseek)+- [Mistral](#mistral)- [Groq](#groq)-- [OCI (Oracle)](#oci-oracle)+- [Cerebras](#cerebras)- [Ollama (Local)](#ollama-local)+- [OpenRouter](#openrouter)- [Vercel AI Gateway](#vercel-ai-gateway)+- [OCI (Oracle)](#oci-oracle)+- [LiteLLM (100+ Providers)](#litellm-100-providers)- [OpenAI-Compatible APIs](#openai-compatible-apis)----## Browser Use+## Browser Use CloudOptimized for browser automation — highest accuracy, fastest speed, lowest token cost.```python-from browser_use import ChatBrowserUse+from browser_use import Agent, ChatBrowserUse+llm = ChatBrowserUse() # bu-latest (default)llm = ChatBrowserUse(model='bu-2-0') # Premium model```@@ -30,62 +68,71 @@ llm = ChatBrowserUse(model='bu-2-0') # Premium model**Models & Pricing (per 1M tokens):**| Model | Input | Cached | Output ||-------|-------|--------|--------|-| bu-1-0 (default) | $0.20 | $0.02 | $2.00 |+| bu-1-0 / bu-latest (default) | $0.20 | $0.02 | $2.00 || bu-2-0 (premium) | $0.60 | $0.06 | $3.50 |+| browser-use/bu-30b-a3b-preview (OSS) | — | — | — |-## Google Gemini+## OpenAI```python-from browser_use import ChatGoogle-llm = ChatGoogle(model="gemini-flash-latest")+from browser_use import Agent, ChatOpenAI++llm = ChatOpenAI(model="gpt-5")```-**Env:** `GOOGLE_API_KEY` (free at https://aistudio.google.com/app/u/1/apikey)+**Env:** `OPENAI_API_KEY` | [Available models](https://platform.openai.com/docs/models)-Note: `GEMINI_API_KEY` is deprecated, use `GOOGLE_API_KEY`.+Supports custom `base_url` for OpenAI-compatible APIs.-## OpenAI+## Anthropic```python-from browser_use import ChatOpenAI-llm = ChatOpenAI(model="gpt-4.1-mini")-# o3 recommended for complex tasks-llm = ChatOpenAI(model="o3")+from browser_use import Agent, ChatAnthropic++llm = ChatAnthropic(model='claude-sonnet-4-6', temperature=0.0)```-**Env:** `OPENAI_API_KEY`+**Env:** `ANTHROPIC_API_KEY` | [Available models](https://docs.anthropic.com/en/docs/about-claude/models)-Supports custom `base_url` for OpenAI-compatible APIs.+Coordinate clicking is automatically enabled for `claude-sonnet-4-*` and `claude-opus-4-*` models.-## Anthropic+## Google Gemini```python-from browser_use import ChatAnthropic-llm = ChatAnthropic(model='claude-sonnet-4-0', temperature=0.0)+from browser_use import Agent, ChatGoogle++llm = ChatGoogle(model="gemini-2.5-flash")+llm = ChatGoogle(model="gemini-3-pro-preview")```-**Env:** `ANTHROPIC_API_KEY`+**Env:** `GOOGLE_API_KEY` (free at https://aistudio.google.com/app/u/1/apikey) | [Available models](https://ai.google.dev/api/models)++Supports Vertex AI via `ChatGoogle(model="...", vertexai=True)`.++Note: `GEMINI_API_KEY` is deprecated, use `GOOGLE_API_KEY`.## Azure OpenAI+Supports the Responses API for codex and computer-use models.+```python-from browser_use import ChatAzureOpenAI+from browser_use import Agent, ChatAzureOpenAI+llm = ChatAzureOpenAI(- model="gpt-4o",+ model="gpt-5",api_version="2025-03-01-preview",azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),api_key=os.getenv("AZURE_OPENAI_API_KEY"),)```-**Env:** `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_KEY`--Supports Responses API for models like `gpt-5.1-codex-mini`.+**Env:** `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_KEY` | [Available models](https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure)## AWS Bedrock```python-from browser_use import ChatAWSBedrock+from browser_use import Agent, ChatAWSBedrock+llm = ChatAWSBedrock(model="us.anthropic.claude-sonnet-4-20250514-v1:0", region="us-east-1")# Or via Anthropic wrapper@@ -93,49 +140,81 @@ from browser_use import ChatAnthropicBedrockllm = ChatAnthropicBedrock(model="us.anthropic.claude-sonnet-4-20250514-v1:0", aws_region="us-east-1")```-**Env:** `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_DEFAULT_REGION`+**Env:** `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_DEFAULT_REGION` | [Available models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html)++Supports profiles, IAM roles, SSO via standard AWS credential chain. Install with `pip install "browser-use[aws]"`.++## DeepSeek++```python+from browser_use import Agent, ChatDeepSeek++llm = ChatDeepSeek(model="deepseek-chat")+```++**Env:** `DEEPSEEK_API_KEY` | [Available models](https://api-docs.deepseek.com/quick_start/pricing)++## Mistral++```python+from browser_use import Agent, ChatMistral++llm = ChatMistral(model="mistral-large-latest")+```-Supports profiles, IAM roles, SSO via standard AWS credential chain.+**Env:** `MISTRAL_API_KEY` | [Available models](https://docs.mistral.ai/getting-started/models/models_overview/)## Groq```python-from browser_use import ChatGroq+from browser_use import Agent, ChatGroq+llm = ChatGroq(model="meta-llama/llama-4-maverick-17b-128e-instruct")```-**Env:** `GROQ_API_KEY`+**Env:** `GROQ_API_KEY` | [Available models](https://console.groq.com/docs/models)-## OCI (Oracle)+## Cerebras```python-from browser_use import ChatOCIRaw-llm = ChatOCIRaw(- model="meta.llama-3.1-70b-instruct",- service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",- compartment_id="your-compartment-id",-)+from browser_use import Agent, ChatCerebras++llm = ChatCerebras(model="llama3.3-70b")```-Requires `~/.oci/config` setup. Auth types: `API_KEY`, `INSTANCE_PRINCIPAL`, `RESOURCE_PRINCIPAL`.+**Env:** `CEREBRAS_API_KEY` | [Available models](https://inference-docs.cerebras.ai/models/overview)## Ollama (Local)```python-from browser_use import ChatOllama+from browser_use import Agent, ChatOllama+llm = ChatOllama(model="llama3", num_ctx=32000)```-Requires `ollama serve` running locally. Use `num_ctx` for context window (default may be too small).+[Available models](https://ollama.com/library). Requires `ollama serve` running locally. Use `num_ctx` for context window (default may be too small).++## OpenRouter++Access 300+ models from any provider through a single API.++```python+from browser_use import Agent, ChatOpenRouter++llm = ChatOpenRouter(model="anthropic/claude-sonnet-4-6")+```++**Env:** `OPENROUTER_API_KEY` | [Available models](https://openrouter.ai/models)## Vercel AI GatewayProxy to multiple providers with automatic fallback:```python-from browser_use import ChatVercel+from browser_use import Agent, ChatVercel+llm = ChatVercel(- model='anthropic/claude-sonnet-4',+ model='anthropic/claude-sonnet-4-6',provider_options={'gateway': {'order': ['vertex', 'anthropic'], # Fallback order@@ -144,7 +223,34 @@ llm = ChatVercel()```-**Env:** `AI_GATEWAY_API_KEY` (or `VERCEL_OIDC_TOKEN` on Vercel)+**Env:** `AI_GATEWAY_API_KEY` (or `VERCEL_OIDC_TOKEN` on Vercel) | [Available models](https://vercel.com/ai-gateway/models)++## OCI (Oracle)++```python+from browser_use import Agent, ChatOCIRaw++llm = ChatOCIRaw(+ model="meta.llama-3.1-70b-instruct",+ service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",+ compartment_id="your-compartment-id",+)+```++Requires `~/.oci/config` setup and `pip install "browser-use[oci]"`. [Available models](https://docs.oracle.com/en-us/iaas/Content/generative-ai/imported-models.htm). Auth types: `API_KEY`, `INSTANCE_PRINCIPAL`, `RESOURCE_PRINCIPAL`.++## LiteLLM (100+ Providers)++Requires separate install (`pip install litellm`).++```python+from browser_use.llm.litellm import ChatLiteLLM++llm = ChatLiteLLM(model="openai/gpt-5")+llm = ChatLiteLLM(model="anthropic/claude-sonnet-4-6")+```++Supports any [LiteLLM model string](https://docs.litellm.ai/docs/providers). Useful when you need a provider not covered by the native integrations above.## OpenAI-Compatible APIs@@ -162,23 +268,11 @@ llm = ChatOpenAI(model="Qwen/Qwen2.5-VL-72B-Instruct", base_url="https://api-inf```**Env:** `MODELSCOPE_API_KEY`-### DeepSeek-```python-llm = ChatOpenAI(model="deepseek-chat", base_url="https://api.deepseek.com")-```-**Env:** `DEEPSEEK_API_KEY`-### Novita```pythonllm = ChatOpenAI(model="deepseek/deepseek-r1", base_url="https://api.novita.ai/v3/openai")```**Env:** `NOVITA_API_KEY`-### OpenRouter-```python-llm = ChatOpenAI(model="deepseek/deepseek-r1", base_url="https://openrouter.ai/api/v1")-```-**Env:** `OPENROUTER_API_KEY`--### Langchain+### LangChainSee example at [examples/models/langchain](https://github.com/browser-use/browser-use/tree/main/examples/models/langchain).