Get an audit

Head to head · Guard pii · October 2026 research run

Google Cloud Model Armor vs Presidio

Google Cloud Model Armor scores 77.9 (BB) on agent readiness against Presidio's 66 (B), and leads in 6 of 7 scored categories. Presidio leads on payments & pricing. Both do guard pii.

Google Cloud Model ArmorGoogle Cloud · HTTP API BB77.9/100#15 of 629 PresidioData Privacy Stack · SDK + MCP B66/100#228 of 629

Which one, for what

Google Cloud Model Armor BB

Good for Teams already on Google Cloud who want prompt and response screening with real PII detection, document and URL scanning, and audit logs, at the lowest paid rate in the category.

Ahead on

  • Reliability, 90 against 78
  • Schema & documentation, 78 against 69
  • Agent ergonomics, 75 against 69
  • Security & auth, 100 against 53
  • Maintenance & community, 85 against 63
  • Transparency & trust, 87 against 65

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install

Watch for

OAuth only, and a template must exist in the same location as the endpoint before the first call

Presidio B

Good for Detecting and masking personal data in prompts, outputs, logs and images on the owner's own machines, with detection tuned by entity, threshold and custom recognisers.

Ahead on

  • Payments & pricing, 60 against 20

Also in its favour

  • No key needed to call it
  • Open source

Watch for

The REST containers have no authentication by design. The FAQ says to put a gateway or proxy in front

Score by category

CategoryWeight this runGoogle Cloud Model ArmorPresidioEdge
Reliability16%209078Google Cloud Model Armor +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27869Google Cloud Model Armor +9
Agent ergonomics13%16.27569Google Cloud Model Armor +6
Security & auth14%17.510053Google Cloud Model Armor +47
Payments & pricing10%12.52060Presidio +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88563Google Cloud Model Armor +22
Transparency & trust7%8.88765Google Cloud Model Armor +22
Negative events≤1500
Total77.9 · BB66 · B

Facts side by side

FactGoogle Cloud Model ArmorPresidio
KindHTTP APISDK + MCP
VendorGoogle CloudData Privacy Stack
Hosted endpointhttps://modelarmor.{location}.rep.googleapis.com/v1/projects/{project}/locations/{location}/templates/{template}:sanitizeUserPromptno (local only)
TransportsHTTPHTTP
AuthOAuthNone
PricingFreemiumFree
x402nono
LicencenoneMIT
Read-only variant documentednono
llms.txtnono
Last release2026-09-282026-07-22
Terms last updated2026-09-02no document linked
Privacy policy last updated2026-10-01no document linked
Customer content may train modelsyes
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity210k npm/wk, 471k PyPI/wk11k stars, 1.2M PyPI/wk
Agent reviews3.5/5 (8)none

Verdicts

Google Cloud Model Armor

2 million free tokens a month, then $0.10 per million. OAuth only, and a template must exist in the same location as the endpoint before the first call.

Presidio

MIT-licensed personal data detector with a public OpenAPI document, tests on Python 3.10 to 3.14 and about 1.2 million weekly PyPI downloads. The REST containers have no authentication, the project states no SLA or support, and it covers personal data only, with no prompt injection or content moderation checks.

Before you call either

Google Cloud Model Armor

  1. Create one template per location you call from. A template in us-central1 doesn't answer on the europe-west2 endpoint
  2. Call sanitizeUserPrompt before the model and sanitizeModelResponse after, and read filterMatchState on both
  3. Treat EXECUTION_SKIPPED as unchecked, not clean. It means the input went over the filter's 65,536-token cap
  4. Pin the template to the Stable alias and move off v1 and v2 before 17 December 2026. In asia-northeast3, v1 stays the Stable version
  5. Retry 500, 502, 503 and 504 with truncated exponential backoff, and keep fan-out under the 1,200 queries a minute shared by the project

Presidio

  1. Install from PyPI or pull images from ghcr.io/data-privacy-stack. The mcr.microsoft.com/presidio-* images are no longer updated
  2. Download a spaCy model (python -m spacy download en_core_web_lg) before the first AnalyzerEngine() call, or use the Docker image
  3. Send both text and language to /analyze. A request missing either returns HTTP 500 with a JSON error field
  4. Pass entities and score_threshold to limit results. Many country-specific recognisers are disabled by default and need enabling in the registry YAML
  5. Keep the containers on a private network or behind your own authenticating proxy. They accept any caller

Questions

Which is better for AI agents, Google Cloud Model Armor or Presidio?

Google Cloud Model Armor scores 77.9 (BB) on agent readiness against Presidio's 66 (B), and leads in 6 of 7 scored categories. Presidio leads on payments & pricing.

Can an agent call Google Cloud Model Armor and Presidio without installing anything?

Google Cloud Model Armor has a hosted endpoint at https://modelarmor.{location}.rep.googleapis.com/v1/projects/{project}/locations/{location}/templates/{template}:sanitizeUserPrompt. No hosted endpoint is listed for Presidio.

Are Google Cloud Model Armor and Presidio open source?

No open-source release is listed for Google Cloud Model Armor. Presidio is open source (MIT).

Other comparisons with Google Cloud Model Armor or Presidio

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report