Skip to main content
An AI agent can create its own free Browser Use account without a human opening the dashboard. This is useful when an agent has terminal or HTTP access and needs a Browser Use API key before it can run cloud browser tasks. The flow is a Browser Use agent challenge: the agent requests a challenge, solves the math problem, verifies the answer, and receives an API key.

REST flow

1. Request a challenge

curl -X POST https://api.browser-use.com/cloud/signup \
  -H "Content-Type: application/json" \
  -d '{}'
Request body, optional (include a user email/name if available):
{
  "email": "user@example.com",
  "name": "User Name"
}
Response:
{
  "challenge_id": "uuid",
  "challenge_text": "..."
}

2. Solve the challenge

Read challenge_text and solve the math problem. Return the answer as a string with two decimal places, for example "144.00".

3. Verify the answer

curl -X POST https://api.browser-use.com/cloud/signup/verify \
  -H "Content-Type: application/json" \
  -d '{"challenge_id":"uuid","answer":"144.00"}'
Request body:
{
  "challenge_id": "uuid",
  "answer": "144.00"
}
Response:
{
  "api_key": "bu_..."
}
Use the returned key for Browser Use Cloud API requests. For example, create a browser session:
curl -X POST https://api.browser-use.com/api/v3/browsers \
  -H "X-Browser-Use-API-Key: bu_..." \
  -H "Content-Type: application/json" \
  -d '{}'
See the Create Browser Session API reference.

Claim the account

If a human wants to see the agent-created account in the dashboard later, the agent can create a claim link:
curl -X POST https://api.browser-use.com/cloud/signup/claim \
  -H "X-Browser-Use-API-Key: bu_..."
Response:
{
  "claim_url": "https://..."
}
The claim URL is valid for 1 hour.

CLI flow

Agents with shell access can use the Browser Use CLI instead of calling the REST endpoints directly:
browser-use cloud signup
browser-use cloud signup --verify <challenge-id> <answer>
browser-use cloud signup --claim
The CLI saves the API key to ~/.browser-use/config.json after verification.