Browser agent
Give a goal in plain words; an AI agent does it in a real cloud browser and returns the answer. 3 live · 3 in the catalog.
| Provider | Price | Status |
|---|---|---|
| Do a task in a real browser (Browser Use, GPT-6 Luna)Browser Use | $0.050 / call | Live |
| Walk your signup or checkout like a new customer (Browser Use, GPT-6 Luna)Browser Use | $0.050 / call | Live |
| Read a competitor's pricing plans (Browser Use, GPT-6 Luna)Browser Use | $0.050 / call | Live |
Success rate and speed will show once a provider has 5 real calls in the last 30 days.
Run a comparison
Pick up to 6 live providers. Each one is charged at its own price; failures are free.
Questions
Which Browser agent API is cheapest?
They all cost $0.050 per call. Failed calls are not charged.
How do I call a Browser agent API from an AI agent?
Connect your agent once: paste the message from superpowers.tools/docs into Claude, ChatGPT or Codex. Then ask in your own words, and your agent picks one of these providers and runs it. You pay only when a call works, and new accounts get $5 free. Developers can call POST /v1/run with "tool": "browseruse.run-task" or use the MCP server.
For developersAPI call and the shared input and output format
Call any of them with one API key: POST /v1/run with "tool": "browseruse.run-task", or through the MCP server. Every provider takes the same input and returns the same output, and failed calls are not charged.
Input
{
"type": "object",
"additionalProperties": false,
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"minLength": 10,
"maxLength": 4000,
"description": "What to do in the browser, in plain words, as you would ask a person. Say what to return."
},
"start_url": {
"type": "string",
"format": "uri",
"description": "Optional page to start on"
},
"output_schema": {
"type": "object",
"description": "Optional JSON Schema for the answer; the result comes back as JSON matching it"
},
"max_cost_usd": {
"type": "number",
"minimum": 0.02,
"maximum": 0.5,
"default": 0.15,
"description": "Cap on the agent model spend for this run (US$0.02-0.50). Most short tasks use under US$0.02."
},
"proxy_country": {
"type": "string",
"pattern": "^[a-z]{2}$",
"description": "Optional ISO country code (e.g. br, us) to browse through a residential proxy there. Without it the browser uses a datacenter connection."
}
}
}Normalized output
{
"status": "completed",
"answer": {},
"text": ""
}