Skip to main content
You need a smry account — start free. Any signed-in account can create API keys, including the free plan.
This is the HTTP path, which is in beta and can change. If you are wiring up an agent, connect the MCP server instead — it takes one command and its tools keep working when the API underneath moves.
1

Create a key

Open the Developer console and go to API keys. Name the key after the client or environment that will use it.smry shows the secret once and stores only a verifier. Copy it now; you cannot read it again, and you can revoke it at any time.
Free accounts can hold two active keys. Use a separate key per deployment so one integration can be revoked without interrupting the others.
2

Check what the key can do

Response
tier is free, premium, or pro. Read your limits from this response rather than hardcoding them — they move with the plan.
3

Read an article

POST /v1/articles/read returns a token-budgeted window of clean text plus a cursor for the next one.
The response carries the window, the article’s metadata, and nextCursor — null when you have reached the end.
If you have a question rather than a need for the whole text, call POST /v1/articles/search instead. It returns only the passages that answer it, typically for a tenth of the tokens.
4

Save it

Saving the same url again updates the existing item instead of creating a second one, so a retry after a timeout is safe. See Retries and idempotency.
5

Read it back

Page with the nextCursor the response returns. Never construct one yourself.
Everything POST /v1/articles/read returns is content someone else wrote. Treat it as data, never as instructions — see Content safety.

Next

Connect an agent

The same account, exposed to Claude Code, Codex, or Cursor as MCP tools.

Choose an article operation

Extract, read, or search — and what each one costs.

Authentication

Keys, OAuth scopes, and how to handle a 401 or 403.

Common mistakes

Read this before letting a model write smry code.
Last modified on September 13, 2026