CONCENTRATE
Pricing
ModelsDocsRequest a Demo

Data Security

Keep sensitive data out of model traffic

Redact PII, PCI, and PHI in prompts and responses, route workloads to zero-retention providers where required, and keep evidence that the rules ran.

Request a demoRead docs
Data security flow showing sensitive input redacted before safe output with PII and ZDR checks passed
Redaction event

Which rule ran, which entity type was removed, and whether it applied to the prompt or response.

PII

Redacted

Retention

ZDR options

Evidence

Logs

01

Input

Card number

Redacted before provider request.

02

Rule

Support traffic

Applies to support app Universal API key.

03

Review

Passed

Security can see what changed and when.

New capabilities

What your team gains with Concentrate

01

Redact before data reaches a provider

Remove selected entity types from prompts, responses, or both on the path through Concentrate.

02

Route to no-retention providers

Restrict workloads to provider paths that support zero data retention where your policy requires it.

03

Leave evidence for reviewers

Use request logs and audit logs to show which rules applied without logging the sensitive values themselves.

Who Concentrate is designed for

Teams handling regulated or customer data in AI features

Data rules belong where every model request passes through — not in scattered app code that each team maintains differently. Concentrate applies redaction and retention policy per key or team, then leaves a record security can review.

Security and compliance

Redact PII, PCI, and PHI from prompts, responses, or both, with events that prove filtering ran without storing raw values.

Support and customer apps

Tie rules to Universal API keys so support traffic redacts phone numbers while an internal eval key keeps a different policy.

Healthcare and finance workloads

Combine redaction with zero data retention on provider paths that support no retention for the models you use.

Engineering without reimplementing filters

Ship new AI features on keys that inherit org or team policy instead of copying redaction logic into every service.

Data Security basics

Frequently asked questions

Can redaction rules apply to one app without affecting every team?
Yes. Rules can be tied to scoped Universal API keys, teams, or traffic paths. For example, support traffic can redact phone numbers and addresses while an internal eval project keeps a different rule set.
Can Concentrate redact both prompts and model responses?
Yes. Redaction can run on prompts before provider calls, on responses before they return to the app, or both. That matters when users might paste sensitive data into prompts or when a model could return sensitive fields from context.
What should engineers log when a redaction rule fires?
Log the request id, API key, route, rule name, entity type, and whether prompt or response redaction ran. Avoid storing the raw sensitive value unless your internal policy explicitly allows it.
CONCENTRATE

One API for every major LLM provider — routing, spend, logs, and controls in one place.

New York

130 E 59th St, 17th floor

New York, NY 10022

Wilmington

1201 N. Market Street, Suite 200

Wilmington, DE 19801

LLM Gateway
  • LLM Gateway
  • Request Routing
  • Usage Monitoring
  • Spend Management
  • Data Security
  • Access Controls
Teams
  • AI Engineering
  • Engineering Leadership
  • Finance & Operations
  • Security & Compliance
Integrations
  • All Integrations
  • Migration Guides
Platform
  • Pricing
  • Model Fortress
  • Enterprise
  • Documentation
  • Status
Legal
  • Privacy Policy
  • Terms of Service
  • Data Processing Addendum
  • Acceptable Use Policy
Features
  • Universal API Keys
  • Spend Tracking
  • Token Allocation
  • Usage Analytics
  • Request Logs
  • Alerts
  • Data Redaction
  • Zero Data Retention
  • Audit Logs

LLM Gateway

  • LLM Gateway
  • Request Routing
  • Usage Monitoring
  • Spend Management
  • Data Security
  • Access Controls

Teams

  • AI Engineering
  • Engineering Leadership
  • Finance & Operations
  • Security & Compliance

Integrations

  • All Integrations
  • Migration Guides

Platform

  • Pricing
  • Model Fortress
  • Enterprise
  • Documentation
  • Status

Legal

  • Privacy Policy
  • Terms of Service
  • Data Processing Addendum
  • Acceptable Use Policy

Features

  • Universal API Keys
  • Spend Tracking
  • Token Allocation
  • Usage Analytics
  • Request Logs
  • Alerts
  • Data Redaction
  • Zero Data Retention
  • Audit Logs

Offices

New York

130 E 59th St, 17th floor

New York, NY 10022

Wilmington

1201 N. Market Street, Suite 200

Wilmington, DE 19801

© 2026 Concentrate AI. All rights reserved.

CONCENTRATE
Log In
Log In