Jev pricing calculator: how much does Jev cost?

Jev 1.13 costs $0.042 per million input tokens, which is $42 per billion. Output tokens are free and there is no per-request fee, so your bill is purely a function of how much state and how many question definitions you send.

About $0.000042 for a typical request: a 500-token text with four short questions bills roughly 1,000 input tokens, including the ~260-token overhead every request carries, and 1,000 tokens at $0.042 per million is $0.000042. That is $42 per million such requests. A request costs its billed input tokens times $0.042 per million, with no per-request fee and nothing for output. Billing/token/answer observations refer to Jev 1.13 (jev-1.13-20260917) via OpenRouter on 23 September 2026; they were not retested for 1.14 or long context.

A September 2026 VentureBeat report described $5 signup credit. That is historical reporting, not a verified current offer. At $0.042 per million, $5 would cover about 119 million input tokens; under our historical Jev 1.13 overhead assumption this is about 476,000 decisions on the default workload.

Check TypeSafe’s console for current direct signup availability. The pause announced on 22 September 2026 is historical and has not been reverified. OpenRouter documents access without a TypeSafe account and publishes 262,144-token context for Jev 1.13 and 1.14.

The models page publishes a token rate and unpriced custom/enterprise limits, not subscription terms. TypeSafe charges one price per input token with no per-request fee. Its models page says higher rate limits are available on custom and enterprise plans through sales, but it publishes no price for those plans.

Yes. TypeSafe bills input tokens only. Responses still report usage.output_tokens so you can see them, but they are not charged. This is why Jev's advantage grows against any LLM that reasons out loud before answering.

Almost always. Jev ingests the state once and evaluates every question against it in parallel, so N questions in one call pays for the state — and the fixed per-request overhead — once instead of N times. With a 500-token item and four questions, batching cuts the bill by roughly 70 percent. An independent test of 2,976 billed requests found the answers unchanged. Billing/token/answer observations refer to Jev 1.13 (jev-1.13-20260917) via OpenRouter on 23 September 2026; they were not retested for 1.14 or long context.

Because every Jev request also bills a fixed overhead of about 260 input tokens beyond your state and questions. An independent benchmark of 2,976 requests to jev-1.13 (via OpenRouter, billed at exactly input tokens × $0.042 per million) measured it at 261 tokens per request, and TypeSafe's own API example reports 296 input tokens for a one-sentence state with one question. It matters most for small requests, and it is one more reason to batch questions into one call. Billing/token/answer observations refer to Jev 1.13 (jev-1.13-20260917) via OpenRouter on 23 September 2026; they were not retested for 1.14 or long context.

TypeSafe sets tokens-per-second and requests-per-second quotas per organization. Read your current quotas in the developer console; exceeding either returns HTTP 429. No numeric quota applies universally. Policy checked 17 October 2026 against docs.typesafe.ai/models.

Without your organization quotas, throughput is unknown. With both quotas, divide tokens/s by assumed tokens per call and take the smaller of that and requests/s. Whether quota accounting includes the historical ~260-token billing overhead is unverified; choose that assumption explicitly. Billing/token/answer observations refer to Jev 1.13 (jev-1.13-20260917) via OpenRouter on 23 September 2026; they were not retested for 1.14 or long context.

For TypeSafe direct Jev 1.13 and 1.14, defaults are 64,000 tokens for state plus all questions and 32,000 for state plus any one question. TypeSafe-Danger-Zone-Long-Context: true raises both to 262k at the same token price but with slower, less accurate results. OpenRouter separately publishes 262,144 and documents automatic long-context handling.

Under this site's historical September 2026 comparison prices, Jev's estimated token bill is lower for the example classification workloads. Those competitor rates have not been reverified. Enter current vendor prices and your own workload before budgeting; a cheaper token bill does not establish better accuracy.

OpenRouter lists typesafe/jev-1.13 and typesafe/jev-1.14 at $0.042 per million input tokens, output free, 262,144-token context. Its ~typesafe/jev-latest alias points to 1.14; TypeSafe direct jev-latest points to 1.13 and jev-preview to 1.14. Other gateway entries are historical snapshots dated 26 September 2026.

No. This site is about Jev, the System One decision model from TypeSafe AI. JEV is also an abbreviation for Japanese encephalitis virus, which is a completely unrelated medical topic.