Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

use chatbrowseruse() examples in costs and observability docs, update supported models mdx to remove recommendations, move supported models to get started section, updated redirects

Reagan Hsu0d1c66ea9a33
diff --git a/docs/development/monitoring/costs.mdx b/docs/development/monitoring/costs.mdx
index 1701f28c1..069c8bf60 100644
--- a/docs/development/monitoring/costs.mdx
+++ b/docs/development/monitoring/costs.mdx
@@ -10,11 +10,11 @@ mode: "wide"
To track token usage and costs, enable cost calculation:
```python
-from browser_use import Agent, ChatOpenAI
+from browser_use import Agent, ChatBrowserUse
agent = Agent(
task="Search for latest news about AI",
- llm=ChatOpenAI(model="gpt-4.1-mini"),
+ llm=ChatBrowserUse(),
calculate_cost=True # Enable cost tracking
)
diff --git a/docs/development/monitoring/observability.mdx b/docs/development/monitoring/observability.mdx
index f07bcb680..65ecd2c34 100644
--- a/docs/development/monitoring/observability.mdx
+++ b/docs/development/monitoring/observability.mdx
@@ -26,7 +26,7 @@ export LMNR_PROJECT_API_KEY=<your-project-api-key>
Then, you simply initialize the Laminar at the top of your project and both Browser Use and session recordings will be automatically traced.
```python {5-8}
-from browser_use import Agent, ChatOpenAI
+from browser_use import Agent, ChatBrowserUse
import asyncio
from lmnr import Laminar, Instruments
@@ -36,7 +36,7 @@ Laminar.initialize(project_api_key="...", disabled_instruments={Instruments.BROW
async def main():
agent = Agent(
task="open google, search Laminar AI",
- llm=ChatOpenAI(model="gpt-4.1-mini"),
+ llm=ChatBrowserUse(),
)
await agent.run()
diff --git a/docs/docs.json b/docs/docs.json
index 91349591a..cec251d44 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -25,7 +25,11 @@
"redirects": [
{
"source": "/customize/supported-models",
- "destination": "/customize/agent/supported-models"
+ "destination": "/supported-models"
+ },
+ {
+ "source": "/customize/agent/supported-models",
+ "destination": "/supported-models"
},
{
"source": "/customize/agent-settings",
@@ -135,13 +139,13 @@
"pages": [
"introduction",
"quickstart",
- "quickstart_llm"
+ "quickstart_llm",
+ "supported-models"
]
},
{
"group": "Customize",
"pages": [
- "customize/agent/supported-models",
{
"group": "Agent",
"icon": "robot",
diff --git a/docs/customize/agent/supported-models.mdx b/docs/supported-models.mdx
similarity index 94%
rename from docs/customize/agent/supported-models.mdx
rename to docs/supported-models.mdx
index 61b84fbcb..d48651475 100644
--- a/docs/customize/agent/supported-models.mdx
+++ b/docs/supported-models.mdx
@@ -5,17 +5,9 @@ icon: "microchip-ai"
---
-### Recommendations
-
-- Best accuracy: `O3`
-- Fastest: `llama4` on groq
-- Balanced: fast + cheap + clever: `BU 1.0`
-
-`BU 1.0` is our in-house model trained on millions of browser automation tasks, matching the accuracy of top models while completing tasks **3-5x** faster. [See our blog post→](https://browser-use.com/posts/speed-matters)
-
### Browser Use [example](https://github.com/browser-use/browser-use/blob/main/examples/models/browser_use_llm.py)
-Fastest and smartest option, optimized specifically for browser automation.
+`ChatBrowserUse()` is our in-house model trained on millions of browser automation tasks, matching the accuracy of top models while completing tasks **3-5x** faster. [See our blog post→](https://browser-use.com/posts/speed-matters)
```python
from browser_use import Agent, ChatBrowserUse
@@ -36,7 +28,7 @@ Required environment variables:
BROWSER_USE_API_KEY=
```
-Get your API key from the [Browser Use Cloud](https://cloud.browser-use.com/dashboard/api). New signups get \$10 free credit via OAuth or \$1 via email.
+Get your API key from the [Browser Use Cloud](https://cloud.browser-use.com/dashboard/api). New signups get \$10 free credit via OAuth or \$1 via email.
### OpenAI [example](https://github.com/browser-use/browser-use/blob/main/examples/models/gpt-4.1.py)
@@ -264,7 +256,7 @@ Authentication methods supported:
## Ollama
1. Install Ollama: https://github.com/ollama/ollama
-2. Run `ollama serve` to start the server
+2. Run `ollama serve` to start the server
3. In a new terminal, install the model you want to use: `ollama pull llama3.1:8b` (this has 4.9GB)
```python