Skip to content
Jev Pricing

Independent measurements · not TypeSafe AI · we do not sell keys

Jev API access: model IDs, routes and context modes

OpenRouter documents access without a TypeSafe account. Direct signup status must be checked in the console; the September pause is historical. Our measurements used Jev 1.13 via OpenRouter on 23 September 2026, not current 1.14 or long context. New to Jev? What it is, or calculate how much Jev costs for your volume.

  • Get a key now: create an OpenRouter account and add credit
  • Endpoint: POST openrouter.ai/api/v1/systemone
  • Price: $0.042 per 1M input tokens; output is free
  • Context: OpenRouter 262,144; direct default 64k / 32k, with opt-in long context. Historically, each 1.13 call billed ~260 extra tokens
Pick a route

Which way in suits you?

OpenRouterTested here
Its Jev page →

An OpenRouter key with credit, no TypeSafe account. Historical calls below used pinned 1.13; 1.14 has not been benchmarked here.

Key from
OpenRouter
Model ID
typesafe/jev-1.13 or typesafe/jev-1.14; ~typesafe/jev-latest → 1.14
Price
$0.042 / 1M input, output free
Context
262,144 tokens; route-specific long context
curl
curl https://openrouter.ai/api/v1/systemone \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"typesafe/jev-1.13","state":"I was charged twice for March. Please refund one.","questions":{"refund":{"type":"noul","instructions":"Does the customer want a refund?"}}}'

Tested historically: Jev 1.13 (jev-1.13-20260917), OpenRouter, 23 Sep 2026; 1.14 and long context not tested. Checked .

Your first call

What comes back, what it costs, what can go wrong

Reading the request

state is the text you ask about. Each entry in questions is one decision, and noul asks a yes/no question. The answer comes back keyed by the same name, as a probability:

{
  "answers": {
    "refund": {
      "type": "noul",
      "noul": 0.97
    }
  },
  "usage": {
    "input_tokens": 284
  }
}

The shape of a response; your probability will differ.

What it costs

This exact call bills about 284 tokens, most of it the fixed per-call overhead. A thousand of them cost about $0.012; a million, about $11.93.

Estimate your own request →Monthly cost of a workload

If it fails

400
The body is wrong, or the request is too big: we saw 400 for every request past the context limit.
401
The key is missing or not valid for this route.
402
No credit on the account. OpenRouter and Cloudflare both answered 402 until credit was added.
429
Organization rate quota exceeded; check console tokens/s and requests/s. Back off and honor retry-after.
All routes

Every route side by side

TypeSafe and OpenRouter checked 2026-10-17; other rows are historical 2026-09-26 snapshots.
  • OpenRouterNo TypeSafe account

    262,144 tokens; route-specific long context context · $0.042 / 1M input, output free · snapshot 2026-10-17

    typesafe/jev-1.13 or typesafe/jev-1.14; ~typesafe/jev-latest → 1.14

    Tested historically: Jev 1.13 (jev-1.13-20260917), OpenRouter, 23 Sep 2026; 1.14 and long context not tested.

  • TypeSafe directNeeds TypeSafe key

    Default 64k / 32k; opt-in 262k / 262k context · $0.042 / 1M input, output free · snapshot 2026-10-17

    jev-latest → jev-1.13.0; jev-preview → jev-1.14.0

    Not tested here: signup was closed when we tried.

  • Vercel AI GatewayNo TypeSafe account

    Historical 32K listing (2026-09-26) context · $0.042 / 1M input, output free · snapshot 2026-09-26

    typesafe-ai/jev

    Not tested here.

  • Netlify AI GatewayNo TypeSafe account

    Historical ~32K listing (2026-09-26) context · Billed in Netlify credits (no Jev rate published) · snapshot 2026-09-26

    jev-latest (gateway mapping not reverified)

    Not tested here.

  • Cloudflare Workers AINo TypeSafe account

    Historical 32K listing (2026-09-26) context · $0.042 / 1M input, output free · snapshot 2026-09-26

    typesafe/jev

    Tested: requests authenticate, then return 402 until AI Gateway credits are loaded.

  • LiteLLMNeeds TypeSafe key

    Upstream TypeSafe mode; check proxy configuration context · TypeSafe's rate (it forwards) · snapshot 2026-09-26

    jev-latest (passed through)

    Not tested here: it forwards to TypeSafe, so it still needs a TypeSafe key.

Also listed, not included: Requesty shows Jev from $0.04 / 1M input plus a 5% pay-as-you-go fee, but its sample calls it through chat completions, which a decision model does not use. We have not verified it works.

Before you pick

Context depends on route and mode

Default budgets and long context are different modes.

TypeSafe direct 1.13 and 1.14 default to 64k tokens in total and 32k for state plus any question. Send the header TypeSafe-Danger-Zone-Long-Context: true on each long request to raise both to 262k. Price per token stays the same; TypeSafe warns it is slower and less accurate.

OpenRouter publishes 262,144 for both versions. Its guide says text over about 32,000 bytes, and every image request, uses long context automatically. Bytes are not tokens; this does not establish other gateway limits.

TypeSafe direct jev-latest points to 1.13, jev-preview to 1.14. OpenRouter ~typesafe/jev-latest points to 1.14. Pin a version to reproduce a benchmark or confidence threshold.

TypeSafe source · OpenRouter source · checked 2026-10-17. Estimate a default-mode request.

Measured

What a call actually costs in time and tokens

479 billed requests through OpenRouter on 2026-09-23, open code and data.
State sizeTokens billedLatency (warm)
1,000 tokens1,286375 ms
4,000 tokens4,317382 ms
8,000 tokens8,354478 ms
16,000 tokens16,429571 ms
24,000 tokens24,502571 ms
32,000 tokens32,579734 ms
  • Reuse the connection. The same small request took 1,630 ms when it had to open a new connection first, against 375 ms on a reused one. Rate limits and latency.
  • Ask several questions per call. Every call bills ~260 extra tokens on top of your text and questions, so one call with four questions costs far less than four separate calls. How much less.
  • No hidden charges seen. In our OpenRouter test the bill matched tokens × $0.042 / 1M, with nothing extra.
FAQ

Jev API questions

How do I get a Jev API key without a TypeSafe account?

OpenRouter documents access without a TypeSafe account. The September direct-signup pause is historical; check the console for current availability. Other gateway entries retain their September snapshot dates.

Which endpoint and model ID do I use?

Direct: POST https://api.typesafe.ai/v1/systemone with model jev-latest. OpenRouter: POST https://openrouter.ai/api/v1/systemone with typesafe/jev-1.13, the same body. Vercel: typesafe-ai/jev through the AI SDK's evaluate API. Cloudflare: typesafe/jev through Workers AI.

Is the Jev API price the same on every route?

TypeSafe and OpenRouter publish $0.042 per million input tokens, output free, for 1.13 and 1.14. Other prices are historical snapshots. The ~260-token overhead was measured on OpenRouter Jev 1.13 on 23 September 2026.

Do the gateways give the same context window as TypeSafe?

Check the route and mode. Direct defaults: 64k total / 32k state plus any question. TypeSafe-Danger-Zone-Long-Context: true raises both to 262k with slower, less accurate results. OpenRouter publishes 262,144; its guide describes automatic long context above about 32,000 text bytes and for images. Other gateway sizes here are historical snapshots.

What do Jev API errors 400, 401, 402 and 429 mean?

400: the body is malformed or the request is over the context limit (we saw 400 for every over-limit request). 401: the key is missing or invalid for that route. 402: the account has no credit; OpenRouter and Cloudflare both returned it until credit was added. 429: a rate limit; back off and honour retry-after.

How fast is the Jev API?

In our historical 23 September 2026 Jev 1.13 test through OpenRouter, a request with 1,000 tokens of state took 375 ms on a warm connection and 32,000 tokens took 734 ms; the same small request on a fresh connection took 1,630 ms, handshake included. Reuse connections.

Is there a free Jev API?

Current free API availability has not been verified. Historically, Vercel's launch promotion made Jev free on AI Gateway until 25 September 2026; its September listing was $0.042 per 1M input. Accounts opened during TypeSafe's open signup got $5 of credit, reported by VentureBeat. These historical offers are not confirmed as current.

Get an email when TypeSafe reopens direct signup

The September pause is historical. Check the console for current signup availability.

Optional

This site is independent of TypeSafe and cannot give you an account.

How we handle your email
  • What: your email, requested notices, the page path and the consent date/version. The notify-list database does not store your IP address.
  • Why: only to send the notices you asked for, on your consent. We do not sell your email; Cloudflare processes it as described below.
  • Where: a Cloudflare D1 database. Cloudflare Turnstile checks the form for bots and processes browser signals and your IP address to do it (its privacy policy).
  • How long: until you remove it. The first email asks you to confirm; addresses not confirmed within 30 days of it are deleted.
  • Your rights: remove your address with the link above at any time, or write to privacy@a3i.ai to see, correct or delete what we hold.

Snapshots retain their dates (oldest: 2026-09-26); current TypeSafe and OpenRouter facts checked 2026-10-17; the signup pause is TypeSafe’s post. Measurements: jev-fanout-bench. 2 of 6 routes were called by us; the rest are marked. This site is independent of TypeSafe AI and does not sell API access.