PerplexityPII-Tracer

External Link

PII-Tracer is Perplexity's compact 0.6B bidirectional Qwen3 encoder for detecting and redacting personally identifiable information in multilingual conversations.

Token context
4,096 tokens
Inputs
Text
Outputs
Text
Released
Sep 1, 2026

Providers & Pricing

0 current sourced offerings

No Current Hosted API Offering VerifiedThis record is a downloadable or self-hosted artifact. Its cost depends on the infrastructure and serving configuration, not a universal model price.

At a Glance

Model Facts

Identity

Status
active
Developer ID
perplexity-ai/pplx-pii-masking
Released
Sep 1, 2026
Version
PII-Tracer
License
mit

Capacity

Token context
4,096 tokens
Maximum output
Unknown
Total parameters
596,090,241
Active parameters
Unknown
Knowledge cutoff
Not reported

Interface and Access

Inputs
Text
Outputs
Text
API available
No
Open weights
Yes
Self-hostable
Yes
Reasoning
No
Vision
No
Tool calling
No
Capabilities
classification, pii-detection, redaction, sensitivity-classification, token-classification

This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.

Version Lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesperplexity-ai/pplx-pii-masking, PII-Tracer, pplx-pii-masking

Explicit Unknowns

  • Maximum output
  • Tokenizer
  • Knowledge cutoff

Primary Evidence

Sources and Observation Date

Comparable Peers

Related Model Comparisons

All comparisons →
APairBContext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext

Questions

PII-Tracer FAQs

What is PII-Tracer?+

PII-Tracer is Perplexity's compact 0.6B bidirectional Qwen3 encoder for detecting and redacting personally identifiable information in multilingual conversations. It is developed by Perplexity and its current sourced lifecycle status is active.

What inputs and outputs does PII-Tracer support?+

PII-Tracer's current record lists Text as input and Text as output.

How much context does PII-Tracer support?+

The current record lists a 4,096-token context window and does not report a maximum output length.

Is PII-Tracer available through an API?+

PII-Tracer is explicitly marked as not API-available in the current record.

How large is PII-Tracer?+

The current record lists 596,090,241 total parameters and an unknown active parameter count. Its architecture is PiiMaskingModel with bidirectional Qwen3 encoder.

What capabilities and tasks does PII-Tracer support?+

PII-Tracer's recorded capabilities are classification, pii-detection, redaction, sensitivity-classification, and token-classification. Its supported tasks are pii-detection, text, and token-classification.

How much does PII-Tracer cost through an API?+

PII-Tracer has no verified hosted API offering, so no provider token price applies. It is a downloadable or self-hosted artifact whose cost depends on the serving infrastructure and workload.

Can PII-Tracer be self-hosted?+

PII-Tracer is an open-weight model. Self-hosting is supported, and the recorded license is mit.

Does PII-Tracer have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are perplexity-ai/pplx-pii-masking, PII-Tracer, and pplx-pii-masking.

Which models can PII-Tracer be compared with?+

The current compatible peer set includes granite-guardian-4.1-8b, MolmoWeb 4B, MolmoWeb 8B, PaddleOCR-VL-1.5, and ERNIE-4.5-0.3B-PT. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons

Send Feedback