API· Last updated 2026-09-21

Jev API Response Schema

A successful System One response contains model (versioned id that actually ran), answers (one entry per question id), and usage (input_tokens, output_tokens). Answer objects carry a type matching the question. This site does not sell, issue, or proxy TypeSafe keys. Authenticate with a credential you already have from the console or a documented gateway.

Related search language: Jev API response schema, TypeSafe Jev, Jev decision model, decision automation.

See also the api hub.

Jev API Response Schema: context

The quick-start sample (Stripe ticket) illustrates department.choice, frustration.score, and is_urgent.noul. Those values are TypeSafe’s illustration for that state, not a benchmark you should cite as a jev.pro score.

Jev API Response Schema: inputs

You do not “input” a response schema — you consume it. HTTP errors use a different JSON body plus status 401/422/429/529. Do not parse error bodies as answers.

Jev API Response Schema: decision logic

Noul answer: noul in [0, 1]. Choice: choice, probabilities (sum to 1), confidence. Score: score (can land between levels), legend, probabilities, confidence.

SDKs add convenience maps (response.nouls, choices, scores in Python). HTTP clients should read answers.

Jev API Response Schema: implementation notes

Always log model and usage.input_tokens (the billable quantity on the public price list). Output tokens are reported and currently free — confirm on the models page.

Treat the response as the source of truth for what was asked; do not reconstruct answers from logs that omitted probabilities.

FAQ

What is the evaluation URL?

According to TypeSafe documentation: POST https://api.typesafe.ai/v1/systemone.

What is the difference between jev-1.13 and jev-1.13.0?

TypeSafe’s models page uses jev-1.13 as the product line and jev-1.13.0 as the versioned id. Aliases are jev-latest and jev-preview. Do not send a truncated id unless that page lists it.

Are prices and rate limits on this page ours?

No. They are vendor-published list figures. Confirm on docs.typesafe.ai/models. Limits can change without notice.

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.

Primary documentation: https://docs.typesafe.ai. Never treat jev.pro as TypeSafe official documentation. We do not sell, issue, or proxy API keys.