Skip to main content
All endpoints across Agent, Runs, Browser Context Profiles, and Vault are documented across the pages below. All requests require the X-API-Key header unless noted otherwise. See Authentication. For wallet balance and top-ups, see Wallet. Each page below covers one resource end to end — request/response schema, every field, every error. Start with Agent if you’re creating runs; jump to Runs once you have a run_id and need to poll, cancel, or fetch screenshots; use Browser Context Profiles or Vault only if your runs need saved login state or password-manager credentials.

Agent

Run an agent synchronously, asynchronously, in a batch, or via SSE

Runs

List, retrieve, and cancel runs; fetch step screenshots and HTML

Browser Context Profiles

Create, manage, and set up saved browser sessions

Vault

Connect password managers and sync credentials

​
Error Codes

Common HTTP-level errors across automation endpoints: The COMPLETE SSE event or GET /v1/runs/{id} may also include run-level failures such as TASK_FAILED, SITE_BLOCKED, MAX_STEPS_EXCEEDED, TIMEOUT, or BILLING_REJECTED.

TinyAgent overview

First request, endpoint selection, and goal-writing basics

Structured Output

Schema support, limits, and common rewrites

Runs

Statuses, polling, and lifecycle behavior

Goal prompting guide

Improve automation reliability

Authentication

API key setup and troubleshooting

Vault Credentials

Use password manager credentials in runs

Browser Context Profiles

Reuse saved logged-in browser state