API · Last updated 2026-09-21

Jev API status endpoint

“What’s the status of decision X?” is answered by your database after a synchronous evaluation (or after your worker finishes). There is no documented TypeSafe /v1/status for decisions.

This page is for builders who searched an extra “endpoint” name while wiring Jev / System One. jev.pro is an independent unofficial field guide — not affiliated with TypeSafe AI. We do not sell or issue keys. Confirm first-party routes on docs.typesafe.ai/api.

The public API reference documents one evaluation route — POST https://api.typesafe.ai/v1/systemone — plus GET /v1/models. This title is not a separate first-party URL in that reference. Treat the capability as something you implement around the official call.

Steps

1. Generate a decision id when you accept work.
2. Call POST /v1/systemone (inline or from a worker).
3. Write queued | succeeded | failed | held plus answers.
4. Serve that to clients from your API.

Map onto the official POST

TypeSafe returns the evaluation once. It does not keep a job you can GET later (in the public reference we used). Success body: model, answers, usage. Choice/Score include confidence; Noul does not. Question ids key answers only.

Do not invent /health. An authenticated GET /v1/models is a cheap ping if you must. Polling api.typesafe.ai with a UUID they never issued will not work. HTTP 200 is not “we auto-acted” — status of the verdict is yours (hold vs execute).

Pin jev-1.13.0 in the worker. Aliases currently resolve there — confirm. Documented errors: 401, 422, 429, 529. Official SDKs retry 429/529. Async is your queue. Vendor-claimed 70ms–500ms figures describe the evaluation, not a job polling SLA. Schema-safe answers still need your held state when confidence is low.

When not to look for /v1/status

If you need long-running jobs, persist queued locally and run the POST in a worker. Marketplace doors may expose their own job APIs — those are not first-party System One.

Pitfalls

• Polling api.typesafe.ai with a UUID they never issued.
• Confusing HTTP 200 with “we auto-acted.” Status of the verdict is yours.
• Inventing /health.
• Expecting TypeSafe to store decision history.

See also

• API hub — synchronous POST
• Async jobs — your worker
• Trace identifiers — ids you generate
• HTTP endpoint — GET /v1/models as a ping

FAQ

Health of the API?

Use an authenticated GET /v1/models if you need a cheap ping. Do not invent /health.

Is this a documented TypeSafe URL?

No.

Async?

Your queue — async jobs.

Where does held live?

In your database, computed from confidence / Noul bands.

What this page does not claim

• Official TypeSafe status, logos, or support.
• That jev.pro sells, issues, or proxies API keys.
• Extra first-party HTTP routes beyond POST /v1/systemone and GET /v1/models unless the API reference lists them.
• Invented latency SLOs, search volume, or unofficial prices. List price and rate limits are vendor claims — confirm on models.
• That a schema-constrained answer is automatically factually correct.

Disclaimer

This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai. Never treat jev.pro as TypeSafe official documentation. We do not sell, issue, or proxy API keys.