MethodPricingCalculatorFAQ

Shadow audit · Migration · Run

Measure what Jev saves your workflows, before you migrate.

A shadow-mode audit on your data, then migration of your AI routing to Jev by TypeSafe AI, with LLM fallback, a decision log and human review.

Book the free pre-qualificationEstimate my savings

Independent service, not affiliated with TypeSafe AI.

01 · The problem

LLM routing costs money, and nobody knows when to trust it.

cost

Every routing decision goes through an LLM billed per token.

trust

Your teams review everything, because they cannot tell when the model is right.

proof

Jev has just launched. Its numbers come from the vendor. Nobody has measured them on your data.

02 · The method

Measure first. Migrate only if the numbers justify it.

  1. step 1free

    Pre-qualification

    30 minutes. A written go or no-go within 48 hours.

  2. step 22 to 4 weeks

    Shadow-mode audit

    We replay a pseudonymised sample of your past decisions on Jev and on your LLM. Nothing changes in production.

  3. step 3after an audit

    Migration, then run

    Gradual rollout, with the kill switch in your hands.

03 · The verdict

An honest verdict, three options.

The audit compares three options on your real cases. The report fills every line with your measured numbers.

option A

Keep your current routing

No change. Serves as the baseline.

API cost / month
to measure
review / month
to measure
error rate
to measure
implementation
none

option B

Calibrate your current LLM

Same model, calibrated confidence threshold.

API cost / month
to measure
review / month
to measure
error rate
to measure
implementation
calibration

option C

Move to Jev

Routing by Jev, LLM fallback, decision log.

API cost / month
to measure
review / month
to measure
error rate
to measure
implementation
migration

The verdict can be not to migrate.

04 · Architecture

Every decision follows a branch. Every branch leaves a trace.

05 · Pricing

Published packages, in euros.

Audit

Pre-qualification

free

30 minutes. A written go or no-go within 48 hours.

Flash Audit

€3,500

1 decision point. Delivered 2 weeks after your DPO signs off in writing.

Pioneer price €2,500 for the first 3 clients, until 31 December 2026. In return, a case study is published without your name. The migration credit is then €500.

Full Audit

€7,500

3 to 5 decision points. Delivered 4 weeks after your DPO signs off in writing.

Migration

Migration S1 point, n8n or Make. 3 weeks, then 30 days of acceptance.€6,000
Migration M3 to 5 points. 6 weeks, then 30 days of acceptance.€12,000
Migration LUp to 8 points, in-house code. 8 to 10 weeks. Price set after the Full Audit.€18,000 to €25,000

After an audit. LLM fallback, decision log, human review and kill switch included.

Run

Run EssentialThreshold monitoring, alerts, monthly report.€350 / month
Run ProPlus: monthly recalibration, 4 hours of maintenance.€650 / month
Run Mid-capPlus: blocking incidents handled within 4 business hours, 8 hours of maintenance.€1,400 / month

3-month commitment, 6 months for Run Mid-cap.

  • Every migration starts with an audit. The Flash Audit gives a €1,000 credit on a migration signed within 60 days, the Full Audit €2,000. Flash then Migration S: €8,500. Full then Migration M: €17,500.
  • Your Jev and LLM usage stays on your own accounts.
  • For businesses only. Prices exclude VAT. French clients: VAT not applicable, article 293 B of the French General Tax Code. EU business clients: reverse charge, you account for VAT in your country.

06 · Calculator

Estimate your savings. Then have them measured.

A point is a place in the workflow where AI picks a branch. The volumes below cover all your points.

Counted at 1.5 minutes each. Adjustable below.

Advanced settings: your real numbers

Leave empty to use the estimate. Enter your bill if you use prompt caching or the Batch API.

Prompt plus the text to classify. 50 output tokens are added.

90%

The rest falls back to your LLM, which is still billed.

40%

Outcomes unfavourable to a person are still reviewed. Capped at the share decided by Jev.

Default €38.2: average hourly labour cost in the euro area in 2025, according to Eurostat.

Net monthly gain

€1,255

Total investment

€11,169

Payback after go-live

8.9 months

current LLM bill
€153
API savings
+ €132
human time freed
+ €1,528
run
− €350
EU hosting
− €55
Have this measured: book 30 min

Estimate based on assumptions. Bill estimated at public prices as of 23/09/2026, per million input and output tokens: Sonnet 5 at $2 and $10, Haiku 4.5 at $1 and $5, Gemini 3.5 Flash-Lite at $0.30 and $2.50. Jev at $0.042 per million input tokens. $1.1463 to €1. Run Essential for 1 point, Run Pro for 3 to 5. Audit credit deducted, if the migration is signed within 60 days. EU hosting at €55 a month. On your side: 10 hours of labelling per point, 300 decisions reviewed during acceptance, €2,000 of legal costs. The human gain is freed time: it only becomes money if those hours are reassigned. Payback is counted from go-live. From signature, add the project duration. Your audit measures your real numbers.

07 · Examples

Two worked examples. Two different lessons.

SME

4,000 tickets a month in n8n on Claude Haiku 4.5, all reviewed in 1.5 minutes each.

Net gain
€1,128 / month
Payback after go-live
9.9 months

The value comes from human time. Token savings are close to zero.

Example computed on assumptions: Jev decides 90% of cases, 40% of reviews disappear. Your audit measures your numbers.

Mid-cap

500,000 decisions a month on Claude Sonnet 5, 3 decision points, 5,000 cases reviewed in 1.5 minutes each.

Net gain with Run Pro
€2,552 / month
Payback after go-live
8.2 months, 11.6 with Run Mid-cap

On tokens alone, the migration does not pay for itself at this volume. With 1,000 tokens cached, payback moves to 11.3 months.

Example computed on assumptions: Jev decides 90% of cases, 40% of reviews disappear. Your audit measures your numbers.

08 · Eligibility

Who it is for, and who it is not for.

Who it is for

  • An LLM in production to classify, route or triage text, in n8n, Make, LangChain or in-house code.
  • For 1 decision point: at least €1,700 a month of LLM spend on these decisions, or 90 hours of human review. For 3 to 5 points: €3,200 or 165 hours. Both gains add up.
  • Jev access in your own name. TypeSafe AI has temporarily paused sign-ups. We check your access during pre-qualification.
  • 400 past decisions per decision point, and your DPO’s written approval before any data is sent.

Who it is not for

  • Data that cannot leave the EU, even pseudonymised.
  • Health data or other special-category data under GDPR Article 9.
  • High-risk cases under the AI Act, such as hiring or credit.
  • Decisions mainly about amounts or dates.
  • Requests for a “GDPR compliant” label.

09 · Guarantees

What protects you.

  1. A refusal before any invoice if you are not eligible.
  2. The audit balance is due only when a report measured on your data is delivered.
  3. No commission from TypeSafe AI. A no-go is a delivered result.
  4. 20% of the migration is due only if the acceptance criteria are met. Otherwise, we fix it for 30 days at our cost. Excluding Jev outages or changes, and scope changes on your side.
  5. Kill switch in your hands, original workflows kept for 90 days, code in your repository.

10 · Exclusions

What is not included.

  • Legal advice.
  • Jev and LLM usage.
  • EU hosting, €30 to €80 a month.
  • Continuity of the Jev service, which depends on TypeSafe AI.
  • 24/7 on-call.

11 · FAQ

Frequently asked questions.

What is Jev?

Jev is a decision model from TypeSafe AI, in early access since September 2026. It does not generate text. It returns a typed choice and a probability that your code can use directly. TypeSafe AI says the probability is calibrated. The audit checks it on your data.

Are you a TypeSafe AI partner?

No. Jev Migration is an independent service. We take no commission from TypeSafe AI, and your Jev access is in your own name.

Jev is in early access. What if we depend on it?

On error, timeout or rate limit, the decision falls back to the LLM automatically. The kill switch sends all traffic back to the LLM in under 5 minutes, without us. TypeSafe AI may retire a Jev version, in which case you must switch versions. Jev sign-ups are also temporarily paused, so we check your access before any commitment.

Our data goes to the United States. What about GDPR?

Yes, it goes to the United States. TypeSafe AI is not certified under the Data Privacy Framework, so the transfer relies on the standard contractual clauses in its DPA. Data is pseudonymised in the EU before sending, which does not make it anonymous. Your DPO gets a data-flow sheet with the Flash Audit, and a full technical file with the Full Audit. We sign an Article 28 processing agreement. We promise neither compliance nor a risk-free transfer.

Does it work in languages other than English?

Jev targets English first. So we calibrate per language, on your data, and every threshold ships with its measured error rate.

What if Jev changes its prices?

You pay Jev directly. Even at 10 times the price, the mid-cap example still saves €1,099 of API spend a month.

You work alone. What if you are unavailable?

The system runs without us. The code, configuration and runbook are in your repository. The kill switch is in your teams’ hands. On M and L migrations, a senior freelancer is named in the contract.

We can do this in-house.

Yes. The open-source building blocks exist. The audit may even conclude that calibrating your current LLM is enough.

4 audits per quarter.

Book 30 minutes.

Have four numbers ready:

  1. Decision volume
  2. LLM in use
  3. API invoices for the last 3 months
  4. Review hours

Étienne Lescot

Independent developer, n8n specialist, based in France.

Book the free pre-qualification

Or by email: contact@jevmigration.com

Independent service, not affiliated with TypeSafe AI.