---
title: GLiNER PII and NuNER Zero on SIE | Superlinked
description: SIE, an open-source inference engine, serves GLiNER PII and NuNER Zero, two open models that find the personal data in a text, in one API call.
canonical_url: https://superlinked.com/models/superlinked-pii-redact
last_updated: 2026-11-07
---

# GLiNER PII and NuNER Zero

Two open models that find the personal data in a text, in one API call.

Model id: `superlinked/pii-redact` · Endpoint: `extract`

Listed under [Redact (PII)](/models#redact) on [the model index](/models.md).

| Accuracy | Time per request | Serverless price |
|---|---|---|
| – (SPIA, F1 · not measured as one model) | 61 ms per document | $0.08 per 1M tokens |

## On the task pages

- [Leave 32% less personal data exposed than AWS Comprehend, 79% cheaper](/redact): 90.9% Personal data masked · 660 documents; 61 ms Time per document; $73 Cost per 1M documents

## Call it

On SIE Serverless:

```python
from sie_sdk import SIEClient

client = SIEClient(api_key="sk-sie-…")

result = client.extract(
    "superlinked/pii-redact",
    {"text": "{\"date_time\": \"1978-03-29 17:28:13\", \"name\": \"Emma A. Platini\", \"street_address\": \"19325 John Motorway, Apt. 488\"}\n{\"date_time\": \"2022-01-02 14:35:18\", \"name\": \"John D. Smith\", \"street_address\": \"456 Oakwood Avenue, Unit 3C\"}\n{\"date_time\": \"2021-12-15 09:19:21\", \"name\": \"Alex N. Thompson\", \"street_address\": \"334 King's Cross, Flat 15B\"}"},
)
for span in result["entities"]:
    print(span["label"], span["text"])
```

## Next to the other PII models

| Model | SPIA, F1 | Time per request | Serverless price | Size |
|---|---|---|---|---|
| [GLiNER PII and NuNER Zero](/models/superlinked-pii-redact.md) `superlinked/pii-redact` | – | 61 ms per document | $0.08 per 1M tokens | – |
| [NuNER Zero](/models/numind-nuner_zero.md) `numind/NuNER_Zero` | 0.463 | – | $0.05 per 1M tokens | 449M |
| [gliner multi pii v1](/models/urchade-gliner_multi_pii-v1.md) `urchade/gliner_multi_pii-v1` | 0.377 | – | $0.04 per 1M tokens | 289M |

– = not measured / not timed / not listed.

[All 3 PII models](/models#redact)

## Facts

- Runs: urchade/gliner_multi_pii-v1, numind/NuNER_Zero
- Endpoint: extract

## Evaluation

- Accuracy: Run on SIE against the public dataset named in each figure
- Time: SIE timed on a GPU server with the client alongside, one request at a time
- Prices: Serverless list prices
- Sources: [Task page runs and their inputs](https://huggingface.co/datasets/superlinked/sie-task-evidence)