> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pioneer.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# GLiNER2-PII: PII Detection SLM

> Run GLiNER2-PII, Pioneer's open-source multilingual PII detection SLM, to identify names, emails, phone numbers, and other personal data in text.

GLiNER2-PII is our open-source small language model for detecting and redacting personally identifiable information (PII). At 300 million parameters, it identifies 42 fine-grained PII entity types across 7 languages in a single forward pass.

## Inference GLiNER2-PII in Pioneer

`POST /v1/chat/completions`

Runs GLiNER2-PII over the supplied messages and returns the entities defined in `schema`. Pioneer exposes an OpenAI-compatible endpoint at `https://api.pioneer.ai/v1`, so you call GLiNER2-PII through the standard chat completions route using the model ID `fastino/gliner2-privacy-filter-PII-multi`.

**Request body**

<ParamField body="model" type="string" required>
  The GLiNER2-PII model ID: `fastino/gliner2-privacy-filter-PII-multi`.
</ParamField>

<ParamField body="messages" type="object[]" required>
  The text to scan for PII, in standard OpenAI chat format.
</ParamField>

<ParamField body="schema" type="object" required>
  The extraction schema. Contains an `entities` array listing the PII types to detect. Pass any subset of the 42 supported types (see the [label table below](#what-gliner2-pii-detects)). The example detects `person`, `email`, and `phone_number`.
</ParamField>

<ParamField body="include_confidence" type="boolean">
  Return a confidence score for each detected entity. Set to `true` in the example.
</ParamField>

<ParamField body="include_spans" type="boolean">
  Return the character spans for each detected entity. Set to `true` in the example.
</ParamField>

### Example: PII detection

This request detects three entity types `person`, `email`, and `phone_number` in a single user message.

```bash theme={null}
curl -X POST "https://api.pioneer.ai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_PIONEER_API_KEY>" \
  -d '{
  "model": "fastino/gliner2-privacy-filter-PII-multi",
  "messages": [
    {
      "role": "user",
      "content": "Hi, my name is John Smith. You can reach me at john.smith@acme.com or +1-555-0192."
    }
  ],
  "schema": {
    "entities": [
      "person",
      "email",
      "phone_number"
    ]
  },
  "include_confidence": true,
  "include_spans": true
}'
```

## What GLiNER2-PII detects

GLiNER2-PII recognizes 42 fine-grained PII entity types, organized into seven groups.

| Group                     | Entity types                                                                                                                 |
| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| **Person / names**        | `person`, `full_name`, `first_name`, `middle_name`, `last_name`, `date_of_birth`                                             |
| **Contact / address**     | `email`, `phone_number`, `address`, `street_address`, `city`, `state_or_region`, `postal_code`, `country`                    |
| **Government / tax IDs**  | `government_id`, `national_id_number`, `passport_number`, `drivers_license_number`, `license_number`, `tax_id`, `tax_number` |
| **Banking / payment**     | `bank_account`, `account_number`, `routing_number`, `iban`, `payment_card`, `card_number`, `card_expiry`, `card_cvv`         |
| **Digital identity**      | `username`, `ip_address`, `account_id`, `sensitive_account_id`                                                               |
| **Secrets / credentials** | `password`, `secret`, `api_key`, `access_token`, `recovery_code`                                                             |
| **Sensitive dates**       | `sensitive_date`, `document_date`, `expiration_date`, `transaction_date`                                                     |

Supported languages: English, French, Spanish, German, Italian, Portuguese, and Dutch.