Read the page
browser_readThe current page's text as Markdown (or plain text), read from the live page by the same reader as the Extract API, with the page's URL and the time of the read. Takes the session_id from open_browser. 0.1¢ a step that runs.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"session_id": "<session_id>"
},
"name": "browser_read"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | markdown (the default) or text. | markdown |
| session_id | Yes | The session id open_browser returned. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | The address of the page after the step. | |
| error | No | Why the step failed, when it failed. | |
| title | No | The page title. | |
| read_at | No | When the page was read. | |
| took_ms | No | How long the step took. | |
| price_usd | No | What the step cost, in dollars. |