PII

PII models detect, redact, and extract personally identifiable information and other structured entities from text. Both models below run on CPU for privacy-preserving workflows and select a behavior through the metadata.usecase field. Each request is shown for both the Responses API and the OpenAI-compatible Chat Completions API.

Model	Input /1M	Output /1M	Params	Max tokens
`gliner-multi-pii-v1`	$0.02	$0.05	300M	800
`gliner2-base-v1`	$0.02	$0.05	205M	800

gliner-multi-pii-v1

GLiNER Multi PII is a multilingual PII detection and redaction model that supports on-prem deployments as well. It identifies 40+ personally identifiable entity types — identity, contact, government IDs, financial, medical and more. It works natively across six languages: English, French, German, Spanish, Italian, and Portuguese, so a single model covers multi-market and cross-border data without separate per-language pipelines. Built for zero-shot label, it accepts custom label sets at inference time and supports curated PII catalogues, redaction with label or character masks, and generic NER with user-supplied labels.

References: Model docs • Terms • Privacy

Redaction

Set metadata.usecase to redact and metadata.mask to label to replace detected PII in place with [LABEL] placeholders.

curl https://api.zerogpu.ai/v1/responses \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner-multi-pii-v1",
  "input": "Hello Jane Doe, this is John Doe reaching out regarding my recent order. If you need any additional details, feel free to call me at 415-555-0134 during business hours. You can also email me at [email protected], and I will respond as soon as possible.",
  "metadata": {
    "mask": "label",
    "usecase": "redact"
  }
}'

curl https://api.zerogpu.ai/v1/chat/completions \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner-multi-pii-v1",
  "messages": [
    {
      "role": "user",
      "content": "Hello Jane Doe, this is John Doe reaching out regarding my recent order. If you need any additional details, feel free to call me at 415-555-0134 during business hours. You can also email me at [email protected], and I will respond as soon as possible."
    }
  ],
  "metadata": {
    "mask": "label",
    "usecase": "redact"
  }
}'

Response

{
  "redacted_text": "Hello [PERSON], this is [PERSON] reaching out regarding my recent order. If you need any additional details, feel free to call me at [PHONE_NUMBER] during business hours. You can also email me at [EMAIL], and I will respond as soon as possible.",
  "entities": [
    { "text": "Jane Doe", "label": "person", "start": 6, "end": 14, "score": 0.9982 },
    { "text": "John Doe", "label": "person", "start": 24, "end": 32, "score": 0.9981 },
    { "text": "415-555-0134", "label": "phone number", "start": 133, "end": 145, "score": 0.9725 },
    { "text": "[email protected]", "label": "email", "start": 194, "end": 208, "score": 0.9812 }
  ],
  "entities_by_label": {
    "person": ["Jane Doe", "John Doe"],
    "phone number": ["415-555-0134"],
    "email": ["[email protected]"]
  }
}

Extraction

Set metadata.usecase to extract-pii to detect PII without modifying the source text. Narrow results with categories and a confidence threshold.

curl https://api.zerogpu.ai/v1/responses \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner-multi-pii-v1",
  "input": "Contact John Doe at [email protected] or +1-415-555-0134.",
  "metadata": {
    "usecase": "extract-pii",
    "threshold": 0.5,
    "categories": [
      "identity",
      "contact"
    ]
  }
}'

curl https://api.zerogpu.ai/v1/chat/completions \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner-multi-pii-v1",
  "messages": [
    {
      "role": "user",
      "content": "Contact John Doe at [email protected] or +1-415-555-0134."
    }
  ],
  "metadata": {
    "usecase": "extract-pii",
    "threshold": 0.5,
    "categories": [
      "identity",
      "contact"
    ]
  }
}'

Response

{
  "entities": [
    { "text": "John Doe", "label": "person", "start": 8, "end": 16, "score": 0.9989 },
    { "text": "[email protected]", "label": "email", "start": 20, "end": 36, "score": 0.9776 },
    { "text": "+1-415-555-0134", "label": "phone number", "start": 40, "end": 55, "score": 0.9714 }
  ],
  "entities_by_label": {
    "person": ["John Doe"],
    "email": ["[email protected]"],
    "phone number": ["+1-415-555-0134"]
  }
}

gliner2-base-v1

gliner2-base-v1 is a versatile extraction-and-classification model for the structured tasks that fill most production pipelines. Point it at any text and, with a single API call, pull named entities by your own labels, populate a typed JSON schema straight from messy input, or classify by sentiment, intent, or topic. No fine-tuning and no prompt engineering, just a label set or schema at inference time. Because it’s purpose-built and CPU-optimized, it runs faster and cheaper than routing this work to a general-purpose frontier model. Reach for gliner-multi-pii-v1 when the job is dedicated PII redaction. When you need clean structure out of raw text, this is the model.

References: Model docs • Terms • Privacy

Entity extraction

Set metadata.usecase to ner and pass your own labels to extract named entities.

curl https://api.zerogpu.ai/v1/responses \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner2-base-v1",
  "input": "The application is built with Python 3.11 and uses PostgreSQL 15 for storage. It runs on Kubernetes with Docker containers and communicates via gRPC.",
  "metadata": {
    "labels": [
      "programming language",
      "database",
      "technology",
      "protocol"
    ],
    "usecase": "ner",
    "threshold": 0.3
  }
}'

curl https://api.zerogpu.ai/v1/chat/completions \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner2-base-v1",
  "messages": [
    {
      "role": "user",
      "content": "The application is built with Python 3.11 and uses PostgreSQL 15 for storage. It runs on Kubernetes with Docker containers and communicates via gRPC."
    }
  ],
  "metadata": {
    "labels": [
      "programming language",
      "database",
      "technology",
      "protocol"
    ],
    "usecase": "ner",
    "threshold": 0.3
  }
}'

Response

{
  "entities": {
    "programming language": ["Python 3.11"],
    "database": ["PostgreSQL 15"],
    "technology": ["Kubernetes", "Docker", "gRPC"],
    "protocol": ["gRPC"]
  }
}

Structured JSON extraction

Set metadata.usecase to json and define a schema of field::type::description entries to pull structured records out of free text.

curl https://api.zerogpu.ai/v1/responses \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner2-base-v1",
  "input": "Best regards, John Smith, Senior Software Engineer at Acme Corp. Phone: (555) 123-4567, Email: [email protected], Office: 123 Main Street, Suite 400, San Francisco, CA 94105",
  "metadata": {
    "schema": {
      "contact": [
        "name::str::Full name",
        "title::str::Job title",
        "company::str::Company name",
        "phone::str::Phone number",
        "email::str::Email address",
        "address::str::Office address"
      ]
    },
    "usecase": "json"
  }
}'

curl https://api.zerogpu.ai/v1/chat/completions \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner2-base-v1",
  "messages": [
    {
      "role": "user",
      "content": "Best regards, John Smith, Senior Software Engineer at Acme Corp. Phone: (555) 123-4567, Email: [email protected], Office: 123 Main Street, Suite 400, San Francisco, CA 94105"
    }
  ],
  "metadata": {
    "schema": {
      "contact": [
        "name::str::Full name",
        "title::str::Job title",
        "company::str::Company name",
        "phone::str::Phone number",
        "email::str::Email address",
        "address::str::Office address"
      ]
    },
    "usecase": "json"
  }
}'

Response

{
  "data": {
    "contact": [
      {
        "name": "John Smith",
        "title": "Senior Software Engineer",
        "company": "Acme Corp",
        "phone": "(555) 123-4567",
        "email": "[email protected]",
        "address": null
      }
    ]
  }
}

Classification

Set metadata.usecase to classification and supply a schema mapping each axis to its allowed labels.

curl https://api.zerogpu.ai/v1/responses \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner2-base-v1",
  "input": "I absolutely love this product! The quality is outstanding and the customer service was incredibly helpful.",
  "metadata": {
    "schema": {
      "sentiment": [
        "positive",
        "negative",
        "neutral"
      ]
    },
    "usecase": "classification"
  }
}'

curl https://api.zerogpu.ai/v1/chat/completions \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "x-project-id: YOUR_PROJECT_ID" \
  -d '{
  "model": "gliner2-base-v1",
  "messages": [
    {
      "role": "user",
      "content": "I absolutely love this product! The quality is outstanding and the customer service was incredibly helpful."
    }
  ],
  "metadata": {
    "schema": {
      "sentiment": [
        "positive",
        "negative",
        "neutral"
      ]
    },
    "usecase": "classification"
  }
}'

Response

{
  "classification": {
    "sentiment": "positive"
  }
}

Get Started

Models

Guides

Platform

gliner-multi-pii-v1

Redaction

Extraction

gliner2-base-v1

Entity extraction

Structured JSON extraction

Classification

​gliner-multi-pii-v1

​Redaction

​Extraction

​gliner2-base-v1

​Entity extraction

​Structured JSON extraction

​Classification

gliner-multi-pii-v1

Redaction

Extraction

gliner2-base-v1

Entity extraction

Structured JSON extraction

Classification