What exactly is a token?

A token is a usage credit on anonym.legal. Every analyze, anonymize, or decrypt operation deducts a small number from your account balance. You always see the exact cost before each operation, and credits are only spent on operations that succeed.

How is a billing token different from a tokenized PII placeholder?

They share the word but mean different things. A billing token is the credit you spend on operations. A tokenized PII placeholder (like ) is the technical string that replaces a real name in your text during anonymization. You do not pay per placeholder — you pay per operation.

How many credits come with each plan?

Free: 200 credits per 30-day cycle. Basic (€3 / month): 1,000 credits per 31-day cycle. Pro (€15 / month): 4,000. Business (€29 / month): 10,000. Unused balance does not roll over.

How much does it cost to analyze one page of text?

Measured against the production API: a typical 1 000-character contract costs about 11 tokens (analyze + anonymize at GUI defaults). A 5 000-character contract costs about 32 tokens dense or 10 tokens light. A 50 000-character document with dense personal-data tables costs about 273 tokens; the same document at light PII density costs about 55 tokens. The exact cost appears next to every operation button in the web app and via the free estimate endpoint in the API.

How do I check my current token balance?

In the web app, go to Settings → Account. In the API, call the free /api/mcp/balance endpoint or the anonym_legal_get_balance MCP tool. Both return your remaining balance, cycle start, and cycle end.

How do I estimate cost before running an operation?

Two ways. In the web app, the cost preview appears next to each operation button before you click. In the API, use the free anonym_legal_estimate_cost MCP tool — it returns the exact deduction without running the operation.

What is the rule of thumb for token cost?

Short inputs hit a floor of about 4 tokens for analyze (base cost plus ~0.1 token per selected entity type). Above 1 000 characters at GUI defaults the cost scales at roughly 1 token per 312 characters. A real Anonymize click costs analyze + apply combined. Decrypt is the cheapest operation — a 13 000-character cipher text with 239 PII items decrypts for just 15 tokens.

Does choosing a different operator change the cost?

Replace, redact, mask, and hash all cost the same on the same input — pick whichever fits your privacy goal. Encrypt is the cost outlier: it adds the 0.8 × encryptCount term to apply, costing roughly 3× more at small inputs (less at large ones). If you do not need to recover the originals, prefer one of the non-encrypt operators.

Does the language of the text affect cost?

Cost is driven by characters and detected entities, not by language. A short sentence in any of the 48 supported languages costs only a few credits.

Do unused credits roll over to the next cycle?

No. Allocations and top-ups both reset at the end of each billing cycle. Plan ahead and buy top-ups close to when you will use them.

What happens if I run out of credits mid-task?

The next operation returns a 402 Payment Required response with the exact shortfall. You can buy a top-up immediately (on paid plans) or wait for the cycle to reset.

Can I buy more credits during a cycle?

Yes — on Basic, Pro, and Business plans you can purchase top-ups. Rates: Basic €1 = 250 credits, Pro €1 = 300 credits, Business €1 = 350 credits. Free plan users need to upgrade to enable top-ups.

Do top-up credits expire?

Yes. Top-up credits expire at the next cycle reset, the same as your monthly allocation. They do not carry over.

Do failed operations cost anything?

No. Credits are only deducted after a successful operation. Validation errors, server errors, and rejected requests cost zero credits.

How does AI Entity Creation pricing work?

Creating a custom entity recognizer with AI costs a flat 50 credits per request, deducted from your current cycle balance. The cost is shown before each call and may change with prior notice.

By George Curta · Last updated 2026-05-162026-05-16

Back to the Unit System guide

Docs / Credit System / FAQ

Token System — Frequently Asked Questions

Quick answers about how credits work, what they cost, and how to make the most of your balance.

The basics

What exactly is a token?: A token is a usage credit on anonym.legal. Every analyze, anonymize, or decrypt operation deducts a small number from your account balance. You always see the exact cost before each operation, and credits are only spent on operations that succeed.
How is a billing token different from a tokenized PII placeholder?: They share the word but mean different things. A billing token is the credit you spend on operations. A tokenized PII placeholder (like <PERSON_1>) is the technical string that replaces a real name in your text during anonymization. You do not pay per placeholder — you pay per operation.
How do I check my current token balance?: In the web app, go to Settings → Account. In the API, call the free /api/mcp/balance endpoint or the anonym_legal_get_balance MCP tool. Both return your remaining balance, cycle start, and cycle end.

Allocations & limits

How many credits come with each plan?: Free: 200 credits per 30-day cycle. Basic (€3 / month): 1,000 credits per 31-day cycle. Pro (€15 / month): 4,000. Business (€29 / month): 10,000. Unused balance does not roll over.
Do unused credits roll over to the next cycle?: No. Allocations and top-ups both reset at the end of each billing cycle. Plan ahead and buy top-ups close to when you will use them.

Cost & estimation

How much does it cost to analyze one page of text?: Measured against the production API: a typical 1 000-character contract costs about 11 tokens (analyze + anonymize at GUI defaults). A 5 000-character contract costs about 32 tokens dense or 10 tokens light. A 50 000-character document with dense personal-data tables costs about 273 tokens; the same document at light PII density costs about 55 tokens. The exact cost appears next to every operation button in the web app and via the free estimate endpoint in the API.
How do I estimate cost before running an operation?: Two ways. In the web app, the cost preview appears next to each operation button before you click. In the API, use the free anonym_legal_estimate_cost MCP tool — it returns the exact deduction without running the operation.
What is the rule of thumb for token cost?: Short inputs hit a floor of about 4 tokens for analyze (base cost plus ~0.1 token per selected entity type). Above 1 000 characters at GUI defaults the cost scales at roughly 1 token per 312 characters. A real Anonymize click costs analyze + apply combined. Decrypt is the cheapest operation — a 13 000-character cipher text with 239 PII items decrypts for just 15 tokens.
Does choosing a different operator change the cost?: Replace, redact, mask, and hash all cost the same on the same input — pick whichever fits your privacy goal. Encrypt is the cost outlier: it adds the 0.8 × encryptCount term to apply, costing roughly 3× more at small inputs (less at large ones). If you do not need to recover the originals, prefer one of the non-encrypt operators.
Does the language of the text affect cost?: Cost is driven by characters and detected entities, not by language. A short sentence in any of the 48 supported languages costs only a few credits.

Edge cases

What happens if I run out of credits mid-task?: The next operation returns a 402 Payment Required response with the exact shortfall. You can buy a top-up immediately (on paid plans) or wait for the cycle to reset.
Do failed operations cost anything?: No. Credits are only deducted after a successful operation. Validation errors, server errors, and rejected requests cost zero credits.
How does AI Entity Creation pricing work?: Creating a custom entity recognizer with AI costs a flat 50 credits per request, deducted from your current cycle balance. The cost is shown before each call and may change with prior notice.

Top-ups & expiry

Can I buy more credits during a cycle?: Yes — on Basic, Pro, and Business plans you can purchase top-ups. Rates: Basic €1 = 250 credits, Pro €1 = 300 credits, Business €1 = 350 credits. Free plan users need to upgrade to enable top-ups.
Do top-up credits expire?: Yes. Top-up credits expire at the next cycle reset, the same as your monthly allocation. They do not carry over.

Still have a question?

Reach out to our support team or browse the full glossary and platform documentation.

About this page

We update this page when our platform or the law changes.

Read our founder note for how we work.

Each change shows up in the timestamp at the top.

We follow these rules

GDPR (EU 2016/679).
ISO/IEC 27001:2022.
NIS2 (EU 2022/2555).
HIPAA safe harbor under 45 CFR § 164.514(b)(2).

Our promise

We do not sell your data.

We do not train models on your text.

We store your files in Germany.

You can delete your account at any time.

You own your work.

Where we run

Our servers live in Falkenstein, Germany.

We use Hetzner. They hold ISO 27001 certification.

All data stays in the EU.

Backups run every day.

Need help?

Email support@anonym.legal.

We reply within one business day.

How we test

We run a full check suite on every release.

Each surface gets its own sweep script and report.

Human reviewers spot-check the output each week.

We track recall and precision on a labelled set.

Bad runs block the deploy.

What we never do

We never sell your information to third parties.
We never train models on what you upload.
We never keep your work after you delete it.
We never share keys with any outside firm.
We never run ads inside the product.

Plans in plain words

We sell credits, not seats.

One credit covers one short job.

Long jobs use a few credits each.

You can top up at any time.

Unused credits roll over each month.

Read the plans page for current rates.

Who built this

A small team of engineers and lawyers built this.

We ship from Europe and work in the open.

Our founder note spells out why we started.

Where to start

How the parts fit

A browser add-on cleans text inside Chrome.

A Word plug-in handles drafts in Office.

A small desktop tool works on whole folders.

An agent protocol link feeds large models safely.

All four share one core engine and one rule set.

Words from our team

We started this work after a lunch about cookies.

One friend kept getting odd ads on her phone.

We asked why a court file leaked through a draft.

We sketched the first build on a napkin that week.

By month three we had a tiny demo for a friend.

She used it on her first case the next day.

Common questions we hear

Can the tool read scanned PDFs? Yes, with OCR.

Does it work on long files? Yes, in small chunks.

Can I roll my own rule set? Yes, save it as a preset.

Does it run offline? The desktop build runs offline.

Do you keep my files? No, the cloud build wipes after each run.

Will it learn from my work? No, we never train on inputs.

A short tour of the workflow

Upload a file or paste a snippet of prose.

Pick the entities you want gone from the draft.

Choose a method: replace, mask, hash, encrypt, or redact.

Press run and watch the side panel show each hit.

Skim the result and tweak any rule that misfired.

Save the cleaned file or send it to a teammate.