Skip to main content
Industry leading Web Agent: Tessa is the state-of-the-art browser agent, beating OpenAI’s CUA and Anthropic’s Computer Use across benchmarks. Details in our blog post →Now you have access too!

1. Get Your API Key

Sign up and get your API key at app.heytessa.ai/settings

2. Run Your First Agent

curl -X POST "https://api.heytessa.ai/v1/run_browser_agent" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "directive": "Go to news.ycombinator.com and get the titles and points of the top 3 stories on the homepage"
  }'

3. Get Results

The agent typically runs for a few minutes. You have two options:

Option 1: Watch on the Tessa Platform

Visit the history_url from step 2 to:
  • Watch live - See the browser in real-time
  • View step details - Review every action with screenshots
  • Take control - Jump in anytime to guide the agent

Option 2: Poll with the API

Check status and get results programmatically:
curl -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.heytessa.ai/v1/get_job_status/{job_id}"

Configuration Options

VLM Models

Tessa Model Performance Comparison
ModelCredits/StepNotes
claude-sonnet-4-202505145[Default] Recommended for most tasks
gemini/gemini-2.5-flash1Fastest and cheapest option
o33Good accuracy, relatively slower
claude-opus-4-1-2025080525Highest accuracy for complex tasks
gpt-4o5Supported but not recommended

Bring Your Own Browser (BYOB)

{
  "directive": "Navigate to the dashboard and extract the monthly revenue",
  "cdp_url": "ws://localhost:9222/devtools/browser/abc123"  
  // Connect to your Chrome browser anywhere
}

Browser Settings

  • width/height: Viewport size (320-4096px)
  • residential_ip: Use residential proxy for geo-restricted sites
  • max_duration_minutes: Max runtime (1-240 min)
  • idle_timeout_minutes: Stop if idle (1-60 min)
  • keep_browser_open: Keep session alive after completion
These options are only used when Tessa spins up a new browser session (not BYOB).

What’s Next?

Tips

  1. Base URL: All API calls go to https://api.heytessa.ai/v1
  2. Auth Header: Include Authorization: Bearer YOUR_API_KEY in all requests
  3. Rate Limits: 10 req/min for browser agent, 60 req/min for status/balance
  4. Watch Live: Use the live_url to see your agent work in real-time
  5. Natural Language: Write directives like you’d instruct a human
  6. Be Specific: Clear instructions get better results
  7. Check Credits: Monitor usage with /v1/get_credit_balance

Launch YC: Tessa API