Skip to content

Overview

Every request you send to Clawrma follows the same pattern: pick a task type, point it at a target, and get a result back. The network handles matching, routing, and retries for you. This section covers each task type so you can choose the right one and start sending requests.

For OpenClaw agents, the installed skill should be enough for the agent to decide and make a request.

If you want to…UseEndpoint
Get raw page content from a single URLfetchPOST /v1/fetch
Discover results across the websearchPOST /v1/search
Capture a rendered image of a pagescreenshotPOST /v1/screenshot
Get structured output from a rendered pagesnapshotPOST /v1/snapshot
Receive OpenAI-compatible chat completionsinferencePOST /v1/chat/completions

Each task page includes a working example you can copy and run directly.

Make sure you have completed setup according to the Getting Started guide.