API · Last updated 2026-09-21

Jev API explain endpoint

System One models are documented as not writing explanations of their reasoning. An “explain API” that returns a paragraph would contradict that product contract. There is no documented /v1/explain.

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. Persist probabilities, confidence / noul, criteria, and the verdict.
2. Show that to reviewers.
3. If you need a paragraph, call an LLM after and label it generated assistance.
4. Do not advertise the paragraph as “Jev’s reason.”

What the official response actually is

Official answers are typed fields. No rationale key in the public reference we used. Choice/Score include probabilities + confidence. Noul includes noul only. The HTTP envelope is JSON; the model is not authoring a completion. Question ids key the map; they are not sent to the model.

Chaining Choices to spell an essay is slow and weak per jaggedness notes. Pin jev-1.13.0 when you compare traces. jev-latest and jev-preview currently resolve to it — confirm. Documented errors: 401, 422, 429, 529. Official SDKs retry 429/529.

Schema-safe ≠ an explanation of the world. A high confidence is a property of the distribution, not a paragraph. Vendor-claimed latency (70ms–500ms / 40x–200x from the launch post) is about judgment speed, not about generating tokens of rationale.

When you still need prose

Call an LLM after the evaluation, feed it the criteria and top-2 probabilities, and label the text as assistance. Keep it out of compliance packets as “Jev said.”

Pitfalls

• Chaining Choices to spell an essay (slow and weak per jaggedness).
• Inventing /v1/explain.
• Advertising LLM prose as Jev’s reason.
• Looking for rationale on a 200 body.

See also

• API hub — typed answers only
• Response format — fields you can persist
• Decision trace — audit record
• Why Jev gives up generation — product contract

FAQ

Is /v1/explain documented?

No.

Isn’t JSON the explanation?

The HTTP envelope is JSON. The model is not authoring a completion.

Why give up generation?

Explainer.

Can I send explain: true in the body?

Not in the public schema we read. Extra fields risk 422.

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.