Pricing

What Jev costs

Input-only pricing, because there is no output to pay for. The interesting question is not the sticker price — it is what the decision used to cost you.

Input: $0.042 per 1M input tokens
Output: Free (no output tokens are generated)
Latency: 70–500ms end-to-end
Context: ~32,000 tokens per request
Free tier: No free-credit or trial program documented at launch

Why is output free?

Because Jev does not generate any. A chat model bills you per token it writes; Jev returns a decision and a probability distribution from a single forward pass. There is no stream of tokens to meter, so the entire cost sits on the input side.

A worked example

Say you are routing support tickets. An average ticket plus your option list is around 500 tokens of state. At $0.042 per 1m input tokens:

python

500 tokens x 1,000,000 tickets  = 500,000,000 input tokens
500M tokens / 1M x $0.042       = $21.00

One million routing decisions ≈ $21

The same job done by asking a frontier chat model to emit JSON costs orders of magnitude more, runs in seconds rather than milliseconds, and needs parsing plus retry logic you have to maintain. That gap — not the raw number — is the pitch.

Where to buy it

TypeSafe AI (first-party) — Official API. Early-access waitlist; keys issued in batches.
OpenRouter — Live as `typesafe/jev-1.13` at $0.042/M input, $0 output, 32K context, ~99.8% availability. Note it will not show up in OpenRouter's default model list — see the gotcha below.
Vercel AI Gateway — Also carries it, as model id `typesafe-ai/jev`, at the same $0.042/M input, $0 output.

Gateway pricing may carry a margin over first-party rates, and the gateway's limits and terms apply instead of TypeSafe's. Check both before committing production traffic.

Is self-hosting cheaper?

Rarely, at this price. A 4B open model on your own GPU has a real hourly floor whether or not you are serving traffic, plus the engineering to build and calibrate it. At $21 per million decisions, the hosted API is hard to beat on cost alone — self-hosting makes sense when you need data residency, offline operation or no vendor dependency. See the open-source options if that is you.