API · Last updated 2026-09-21

Jev API pagination

answers is a complete map for the questions you sent. There is no cursor of leftover options. Pagination, if you need it, is over your rows or evidence — not over Jev’s answer object.

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. Send the questions you need in one request (fan-out).
2. Page your own corpus; each page becomes a new state.
3. Do not expect next_page_token on the evaluation response.
4. For long state, filter — 64k / 32k vendor context limits live on the models page.

Request / response shape

No documented pagination fields on /v1/systemone. GET /v1/models is a small alias list, not a paged catalog we will invent. Choice’s 255 options are one map, one question — do not page criteria or the model never sees option 200. Question ids are not sent to the model.

Inventing /v1/systemone?cursor= is not a first-party route. Multi-row files are your loop — batch pattern. Pin jev-1.13.0 so paged replays are comparable. Aliases currently resolve there — confirm.

Documented errors: 401, 422, 429, 529. Official SDKs retry 429/529. Paging your corpus into many POSTs will hit vendor-claimed 1200 RPM if you forget backoff. Each page meters input (vendor claim: $0.042 / million; output free). Schema-safe completeness of answers ≠ you retrieved the right page of evidence.

When not to paginate Jev

Do not split one Choice’s criteria across calls. Do not stream leftover probabilities. If state is too large, filter fields — do not cursor the model.

Pitfalls

• Truncating criteria across pages (the model never sees option 200).
• Inventing /v1/systemone?cursor=.
• Expecting next_page_token on answers.
• Treating GET /v1/models as a paged model catalog.

See also

• API hub — complete answers map
• Response format — no cursor fields
• Batch pattern — many questions, one state
• State — filter before you hit context claims

FAQ

Is this a documented TypeSafe URL?

No.

255 Choice options — page them?

No. That is one map, one question.

Bulk rows?

Your loop — bulk imports.

Does usage paginate?

No. One usage object per successful call.

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.