How much does Jev cost?

Official models documentation listed $0.042 per million input tokens and free output tokens as of 2026-09-20. Confirm on TypeSafe's page before you budget.

Are there per-request fees?

The published public price we found is token-based on input. We have not seen a separate published per-request fee.

Jev Pricing | Jev AI Hub

Jev API pricing from TypeSafe's official models page: $0.042 per million input tokens, output free, last verified 2026-09-20.

Jev pricing is easy to misquote. This page only repeats figures that appear in a source, and it dates them.

Last verified: 2026-09-20. Updated: 2026-09-20.

Published public price

Item	Official figure	Verified
Model	`jev-1.13.0`	2026-09-20
Input	$0.042 / million tokens	2026-09-20
Input	$42 / billion tokens	2026-09-20
Output	Free	2026-09-20

The same rates feed the Jev Cost Calculator. They live in src/lib/pricing.ts, not in scattered page copy.

What you actually pay for

You pay for tokens in state plus tokens in questions. Official docs emphasize that extra questions are cheap relative to repeating the state. A cookbook on TypeSafe's site reports large savings from batching many questions in one call. That speed/cost multiple is a vendor cookbook result, not an independent test.

Rate limits (not the same as price)

Official models page when last verified:

250,000 tokens per second
1,200 requests per minute

TypeSafe says limits are adjusting dynamically. Crossing either limit returns 429.

Other cost paths

A third-party article reported the same $0.042 / million input price on Vercel AI Gateway under typesafe-ai/jev. We have not independently confirmed Gateway billing in this project. Check Vercel's current table if that is your path.

Enterprise and custom limits: official docs point to sales@typesafe.ai.

Worked estimate

100,000 requests/month, 400 input tokens of state, 3 questions ≈ 40 tokens each:

tokens / request ≈ 520
monthly tokens ≈ 52,000,000
monthly cost ≈ 52 × $0.042 = $2.18

This uses the published input rate and an assumed 40 tokens per question. Real usage comes from the usage object on each response.

When Jev pricing looks attractive

High-volume classification, routing, and filtering where an LLM would burn output tokens to emit JSON.

When it does not matter

If you make a few hundred calls a day, engineering time dominates. If you need generated text anyway, Jev does not replace that bill.

Common mistakes

Hardcoding $0.042 in five files. Use one config.
Forgetting that aliases can change behavior without changing the price row.
Comparing Jev's input price to an LLM's input price and ignoring that the LLM also bills output.

See the API for usage fields and the changelog when TypeSafe updates the models page.

Jev Pricing

Quick answer