Redact CSV for AI

Redact CSV files before sending to AI.

Want to fine-tune on your customer data without leaking it? Want to dump a CSV into ChatGPT to analyze it? Run it through Cypherz first. Cell-by-cell tokenization with the original schema preserved.

  • 01

    Forgiving parser

    Handles unquoted commas, ragged rows, and BOMs — production-grade CSV ingest.

  • 02

    Schema-preserving

    Headers and column order kept intact.

  • 03

    Stream-friendly downstream

    Use the tokenized CSV in any pipeline that accepts CSV — no AI-vendor lock-in.

Upload via the REST API

curl -X POST https://api.cypherz.app/v1/files \
  -H "authorization: Bearer $CYPHERZ_KEY" \
  -F "file=@customers.csv"

Common questions

Frequently asked.

What happens to my CSV file when I upload it?

Cypherz extracts text, detects PII, tokenizes it, and stores the original encrypted (AES-256-GCM, per-project key) for download. You get a tokenized extraction back immediately. Files can be deleted at any time and their encryption key destroyed.

What's the max file size?

25 MB on managed cloud. Configurable up to 100 MB on self-hosted deployments.

Can I download a redacted version of the file?

Yes — GET /v1/files/{id}/redacted returns a downloadable redacted artifact. Text-native formats keep their original shape; binary formats fall back to a clean PDF.

Is the original ever stored unencrypted?

No. From the moment we receive your file, it's encrypted at rest with a project-scoped data encryption key.

Get started

Upload your first CSV now.

Sign up, create a project, copy your API key. The first request is tokenized in under sixty seconds.