/ 01
Short Answer
Jev is billed on input tokens at about $0.042 per million, or $42 per billion. Output tokens are free. Since Jev returns structured decisions rather than generated prose, a small request can cost a fraction of a cent. Your total depends on the state and questions you send.
/ 02
The Jev Model Rate
| Item | Jev 1.13 on OpenRouter |
|---|---|
| Input tokens | $0.042 per million ($42 per billion) |
| Output tokens | No charge |
| Free Jev API allowance | None listed for this paid model |
Check the OpenRouter Jev 1.13 model page for the current public token rate. The listed rate matches TypeSafe’s direct API documentation at review time, but gateway platform fees can affect the cost of buying credits. VerdictKit does not sell a customer-facing API gateway, resell API credits or provide a VerdictKit API key. Configured live playground requests pass through our server to OpenRouter; for your own API integration, use your own OpenRouter or TypeSafe account.
/ 03
Our Plans
Planned plans: pricing and entitlements below describe the intended VerdictKit offering. The billing product name will be VerdictKit, matching verdictkit.com. Checkout, saved judges and batch processing are not active yet. The local playground has a two-run guest trial and a ten-run Google account tier when live credentials are configured. Demo previews remain available.
Run Pack
$19 one time
500 runs
- No expiration
- Save judges and history
- CSV export
Pro
$12 / month
$72 / year · 50% off
Unlimited runs
- Save judges
- History and reuse
- CSV export
Batch
$29 / month
$174 / year · 50% off
Unlimited runs + batch
- Batch file processing
- Team allowance
- Higher concurrency
- No API key or API credits
Free
$0
10 live runs / day with Google sign-in
- 2 guest runs / day without signup
- Choice, Score and Noul
- Full JSON output
- No saved runs
Explore the Jev playground demo now, or read the official API guide for your own integration.
/ 04
Compare Plans
| Capability | Free | Run Pack | Pro | Batch |
|---|---|---|---|---|
| Three types + full JSON | Yes | Yes | Yes | Yes |
| Runs | 10 / day | 500 total | Unlimited | Unlimited |
| Save judges | No | Yes | Yes | Yes |
| History and reuse | No | Yes | Yes | Yes |
| CSV export | No | Yes | Yes | Yes |
| Batch files | No | No | No | Yes |
Trying a typed decision remains free. Repeated use, saved work and workflow features are the planned paid boundary. These entitlements become effective only after the product features launch.
/ 05
What Counts as a Run
This is the planned VerdictKit counting policy:
- One submitted evaluation counts as one run, whether it contains one question or up to ten.
- The two-run guest trial needs no signup. The ten-run Free allowance is tied to a Google account, not an IP address; both reset each day at 00:00 UTC.
- Running a saved judge again counts as a new run.
- Batch files count by item, not by upload.
- Requests that fail with a 4xx or 5xx response do not consume a run.
Demo previews do not consume runs. Live metering requires the configured server key, Turnstile and usage storage.
/ 06
Why Output Tokens Are Free
OpenRouter’s Jev 1.13 model listing charges for input tokens and lists output tokens at $0. Jev returns typed judgments — an option, a score or a yes/no probability — instead of generating prose. The API still reports output token usage, but the current model rate does not charge for those tokens.
/ 07
What One Call Actually Costs
| Calls | At 476 input tokens per call |
|---|---|
| 1 | ~$0.00002 |
| 1,000 | ~$0.02 |
| 10,000 | ~$0.20 |
| 100,000 | ~$2.00 |
| 1,000,000 | ~$20.00 |
The 476-token request is an illustrative size. Actual cost varies with state length and question count; the table multiplies that size by OpenRouter’s current $0.042-per-million model rate and excludes credit-purchase fees, infrastructure and other service costs.
/ 08
Jev vs an LLM on Price
TypeSafe’s use-case map describes a 100x cost advantage for a big-data scenario. A LangChain article also reports TypeSafe’s claim of up to 200x faster inference and 400x lower cost for classification tasks. Both figures are vendor claims about selected workloads, not independent universal benchmarks. Compare your own tasks, model choices and input sizes before projecting savings.
/ 09
How to Get More Out of Your Runs
- Filter state first. Irrelevant detail can lower accuracy and adds input tokens.
- Keep arithmetic in code; Jev 1.13 is weak at precise math.
- If state cannot be filtered deterministically, a Noul can help screen relevance.
Read Jev’s known limitations before building a repeated workflow.
/ FAQ
Frequently asked questions
How much does Jev cost?
OpenRouter currently lists $0.042 per million input tokens for Jev 1.13 and $0 for output tokens. Check its model page before budgeting.
How much does this playground cost?
Demo previews are free today. VerdictKit plans a $0 Free tier, a $19 Run Pack, $12/month Pro and $29/month Batch; paid checkout is not open yet.
Is there a free plan?
Demo previews are free. With live access configured, two guest runs per day need no signup; a free Google account gets ten per day, resetting at 00:00 UTC.
What counts as one run?
Under the planned policy, one submitted evaluation counts once even if it includes several questions; failed 4xx/5xx requests do not count.
Are output tokens really free?
Yes. TypeSafe’s published Jev 1.13 price charges input tokens and lists output tokens as free.
Do you resell the Jev API?
No. VerdictKit plans to sell playground and batch workflow features, not API keys, API credits or a customer-facing gateway. Live playground requests use an internal server relay. Integrate directly with TypeSafe for your own API use.
How much does 1,000 Jev calls cost?
At an illustrative 476 input tokens each, the TypeSafe model cost is about $0.02. Actual inputs vary.
Is Jev cheaper than an LLM?
It can be for selected structured-decision workloads, according to TypeSafe. Compare your own workload before assuming a ratio.