JevStation

Decision model pricing calculator: what Jev, Clef, Decider and Luna Decisions cost for your workload

Enter how many evaluations you run a month, how long the text is and how many questions each call asks. The table estimates input tokens per call for all five decision models, the monthly bill at each vendor’s list price, and the cost on JevStation. The token counts come from our own calls on 2026-10-07, because list prices alone mislead: Perplexity Decider has the lowest price per token but bills the text once per question.

  • JevTypeSafe · $0.042 / M input

    Direct, per month
    $2.66cheapest
    On JevStation, per month
    $137.10
    Input tokens / call
    634
    Credits / call
    1

  • Clef-flashCloudflare · $0.09 / M input

    Direct, per month
    $5.53
    On JevStation, per month
    $137.10
    Input tokens / call
    614
    Credits / call
    1

  • ClefCloudflare · $0.24 / M input

    Direct, per month
    $14.74
    On JevStation, per month
    $270.30
    Input tokens / call
    614
    Credits / call
    2

  • DeciderPerplexity · $0.04 / M input

    Direct, per month
    $3.94
    On JevStation, per month
    $270.30
    Input tokens / call
    986
    Credits / call
    2

  • Luna DecisionsOpenAI · $0.10 / M input

    Direct, per month
    $6.84
    On JevStation, per month
    $137.10
    Input tokens / call
    684
    Credits / call
    1

Estimates from token models fitted to our measured calls. Output tokens are free on all five. Direct prices exclude any gateway fee; the JevStation column is the cheapest mix of one-time credit packs after the 200 sign-up credits.

How the estimate works

Each model’s row uses a token formula fitted to nine or more real calls per model on 2026-10-07 (three text lengths × one, three and five questions), then multiplies by the list price per million input tokens.

ModelList price, inputInput tokens per call, our fit
Jev$0.042 / M260 + 0.163 × characters + 43 × questions
Clef-flash$0.09 / M29 + 0.168 × characters + 111 × questions ¹
Clef$0.24 / M29 + 0.168 × characters + 111 × questions ¹
Perplexity Decider$0.04 / Mquestions × (84 + 0.163 × characters)
OpenAI Luna Decisions$0.10 / M22 + 0.163 × characters + 139 × questions

¹ On Cloudflare Workers AI on 2026-10-04 the text part stopped counting at about 2,048 tokens because the rest was not read. When we retested on 2026-10-07, both on Workers AI and through OpenRouter, Clef read and billed the whole text, so the formula now applies without a cap.

The formulas are for English prose. Code, JSON and Chinese, Japanese or Korean text produce more tokens per character on every model.

Three workloads, priced

At list price, per 100,000 evaluations:

WorkloadJevClef-flashClefDeciderLuna Decisions
Router: 1 question, 300 characters$1.48$1.71$4.56$0.53$2.10
Ticket triage: 3 questions, 1,500 characters$2.66$5.53$14.74$3.94$6.84
Document review: 5 questions, 8,000 characters$7.47$17.35$46.27$27.76$20.21

The cheapest model changes with the shape of the request. Decider wins the router case by a wide margin and loses the document case to everything but Clef.

Sources

Frequently asked questions

Which decision model is the cheapest?
For one question per call, Perplexity Decider: $0.04 per million input tokens and the fewest tokens per single-question call in our tests. For several questions on the same text, Jev or OpenAI Luna Decisions, because Decider reads the text again for every question. The calculator shows the crossover for your numbers.
Why do token counts differ between models with similar prices?
Tokenizers and prompt formats differ, and one model bills differently. We measured: Jev ≈ 260 + 0.163 × characters + 43 × questions; Clef and Clef-flash ≈ 29 + 0.168 × characters + 111 × questions, for the whole text; Luna Decisions ≈ 22 + 0.163 × characters + 139 × questions; Decider ≈ questions × (84 + 0.163 × characters).
Are output tokens charged?
No. All five decision models bill input tokens only; the answer, a few probabilities, is free.
How does JevStation price these models?
Per evaluation in credits, not per token: 1 credit for a standard evaluation (up to 8,000 characters and five questions) and 3 for a large one, doubled for Clef and Perplexity Decider. Credits come in one-time packs, and the first 200 are free on sign-up.
Is going direct cheaper?
At high volume and list price, usually yes: you pay only tokens. You also write and run the integration for each vendor, and Jev direct needs TypeSafe waitlist access. JevStation trades a per-call margin for one key, one request format, a playground, batch runs and refunds on failure.

Related

Make it part of your pipeline

Sign up for 200 free credits, save your own question sets and call the same evaluation from the API.

Create free accountRead the API docs