The full reference for the Coasty API — also available as an OpenAPI schema and as plain text for LLMs.
Start an autonomous task run and follow it to completion
Run your first task
Run your first task, at a glance
Start an autonomous task run and follow it to completion
POST /v1/runs- 01Createtask + machine + key
- 02Streamwatch ordered SSE
- 03Finishsucceeded or failed
- 04Confirmverify final state
Your first autonomous task needs only an API key and an observable goal. Grab a test key from the API keys page (it never bills), then set it in your shell:
export COASTY_API_KEY="sk-coasty-test-your_key_here"Start with POST /v1/tasks. Describe the result in task and send an Idempotency-Key so a retried create cannot start a duplicate run. Coasty chooses and provisions the machine, executes the task, verifies success or failure, and cleans up:
import os, requests
run = requests.post(
"https://coasty.ai/v1/tasks",
headers={
"X-API-Key": os.environ["COASTY_API_KEY"],
"Idempotency-Key": "invoice-download-4821",
},
json={
"task": "Open the billing portal, download the newest invoice, and verify the PDF exists.",
"max_steps": 50,
},
timeout=30,
).json()
print(run["id"], run["status"]) # queuedThe create response begins at queued. Coasty then drives the machine, records each step, and finishes as succeeded, failed, cancelled, or timed_out. Your application can poll, subscribe to the event stream, or receive signed webhooks; it does not need to execute each prediction itself.
Computer-use evals and real-world environments.
© 2026 Coasty
Backed byYCombinator