Open· Last updated 2026-09-21

Jev cost planning

Plan Jev cost from input tokens × vendor unit price × questions strategy, not from a blog TCO. Snapshot date: 2026-09-21. Re-read vendor cards weekly.

Independent. First-party list price (vendor): $0.042 per million input tokens, output free. models. We do not sell keys or committed-use discounts.

Independent angle (cover, do not clone)

Win delta (pricing-and-cost): worked cost calculator per channel; date-stamped; free-tier caveats; no invented volumes.

Formula (yours to fill)

monthly_$ ≈ (avg_input_tokens_per_call / 1e6) × calls × unit_price × (1 + gateway_uplift)

avg_input_tokens ≈ filtered state + all question text. Official: state ingested once per request — batch questions on the same state.

Do not invent calls. Use last month’s ticket count or a measured pilot.

Channel unit prices (vendor cards, 2026-09-21)

Higher limits: TypeSafe says contact sales. We will not invent enterprise SKUs.

Levers that are documented

• Filter state (money + accuracy).
• Many questions, one state (parallel-questions cookbook: they publish 12.2× cheaper vs N calls on their example — vendor-measured).
• Pin versions so an alias move does not change token use silently.
• Do not generate with Jev (it cannot; chaining Choices is the expensive failure mode they warn about).

Worked example (illustrative volumes — replace with yours)

Suppose a pilot measured 800 input tokens/call and 200_000 calls/month on first-party HTTP:

800 / 1e6 × 200_000 × 0.042 ≈ $6.72 / month in TypeSafe list token fees.

That number is arithmetic on assumed volume, not a promise. Add retries, playground, and gateway markup yourselves.

What a finance partner should see

A dated sheet: door, unit price source URL, measured tokens/call, measured calls, retries, gateway uplift, and a note that output is free per TypeSafe’s card. No invented “industry average volume.” If they want 193× savings, send them the vendor blog and your harness, separately.

What this page does not claim

• No search-volume or “customers save 80%” claims.
• Launch-post commentary that prices may be subsidized is theirs.

FAQ

Are output tokens billed? TypeSafe models page: output free; usage.output_tokens still appears.

Is there a free tier? Not described on the public models page we used. Third-party promos expire.

Does jev.pro sell tokens? No.

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.

Open-cluster pages are independent field-guide notes. Replicas and third-party interfaces mentioned anywhere on jev.pro are not Jev and not endorsed. Hub: Open. Siblings: pricing, channels compared, latency planning. Canonical: https://docs.typesafe.ai.