---
title: GLiNER relex Large on SIE | Superlinked
description: SIE, an open-source inference engine, serves GLiNER relex Large, an open extraction model that pulls entities, and the relations between them, out of text.
canonical_url: https://superlinked.com/models/knowledgator-gliner-relex-large-v1-0
last_updated: 2026-11-07
---

# GLiNER relex Large

An open extraction model that pulls entities, and the relations between them, out of text.

Model id: `knowledgator/gliner-relex-large-v1.0` · Endpoint: `extract` · [Hugging Face](https://huggingface.co/knowledgator/gliner-relex-large-v1.0)

Listed under [Knowledge graph](/models#knowledge-graph) on [the model index](/models.md).

| Accuracy | Time per request | Serverless price |
|---|---|---|
| – (FewRel, F1 · not measured) | – (Not timed one request at a time) | $0.22 per 1M tokens |

## On the task pages

- [Build knowledge graphs on par with Claude Sonnet 5.5, 99% cheaper](/knowledge-graph): 110 Relations right · Claude Sonnet 5.5 = 100; $48 Cost per 1M articles

## Call it

On SIE Serverless:

```python
from sie_sdk import SIEClient

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

text = "David Michael Draiman (born March 13, 1973) is an American singer who is best known as the lead vocalist of the band Disturbed as well as the band Device. Draiman is known for his distorted voice and percussive singing style. In November 2006, Draiman was voted number 42 on the Hit Paraders \"Top 100 Metal Vocalists of All Time\". Draiman has written some of Disturbed's most successful singles, such as \"Stupify\", \"Down with the Sickness\", \"Indestructible\", and \"Inside the Fire\". In October 2011, Disturbed entered a hiatus. Draiman announced in the following year that he was working on an industrial rock / metal project with Geno Lenardo, formerly of Filter, which was later named Device. In June 2015, Disturbed released their first single since their hiatus, named \"The Vengeful One\". They produced it over a year before, and along with it announced a new album, Immortalized."
result = client.extract(
    "knowledgator/gliner-relex-large-v1.0",
    {"text": text},
    labels=[
        "person", "organization", "location", "date",
        "work, product or event",
    ],
    options={
        "relation_labels": [
            "country of citizenship", "notable work",
            "part of", "performer", "publication date",
            "participant of", "member of",
            "country of origin", "date of birth",
            "cast member", "inception", "record label",
        ],
        "threshold": 0.3,
        "relation_threshold": 0.7,
    },
)
for relation in result["relations"]:
    print(relation["head"], relation["relation"], relation["tail"])
```

## Next to the other relation models

| Model | FewRel, F1 | Time per request | Serverless price | Size |
|---|---|---|---|---|
| [GLiNER relex Large](/models/knowledgator-gliner-relex-large-v1-0.md) `knowledgator/gliner-relex-large-v1.0` | – | – | $0.22 per 1M tokens | 467M |
| [gliner2 large v1](/models/fastino-gliner2-large-v1.md) `fastino/gliner2-large-v1` | 0.435 | – | $0.186 per 1M tokens | 486M |
| [gliner2 base v1](/models/fastino-gliner2-base-v1.md) `fastino/gliner2-base-v1` | 0.400 | – | $0.0929 per 1M tokens | 208M |
| [glirel large v0](/models/jackboyla-glirel-large-v0.md) `jackboyla/glirel-large-v0` | 0.264 | – | Not on Serverless (run in your cloud) | 467M |

– = not measured / not timed / not listed.

[All 4 relation models](/models#knowledge-graph)

## Facts

- Size: 467M parameters
- License: Apache-2.0
- Reads: Text, up to 2,048 tokens
- Endpoint: extract

## Evaluation

- Accuracy: Run on SIE against the public dataset named in each figure
- Prices: Serverless list prices
- Sources: [Task page runs and their inputs](https://huggingface.co/datasets/superlinked/sie-task-evidence)