RESEARCH
New capabilities with GliNER-2
Entity extraction. Identify people, companies, products, locations, and custom entity types.
Learn more
Text classification. Assign labels, categories, or intents to any text.
GLiNER-2 Docs
Structured parsing. Convert messy text into clean JSON or database-ready fields.
Try GLiNER-2
EFFICIENCY
Efficiency at Scale
Lower cost
Run high quality NER and classification with significantly lower inference costs.
Low latency
Production ready
130 ms
Average latency
per request
2x
Price efficiency
versus GPT
1000x
Inference speed vs
Generic LLMs
600,000+
![](data:image/svg+xml,<svg display="block" role="presentation" viewBox="0 0 1130 232" xmlns="http://www.w3.org/2000/svg"><path d="M 223.21 3.766 L 234.545 2.013 L 534.483 35.731 L 558.025 0 L 571.975 0 L 595.517 35.731 L 895.455 2.013 L 906.79 3.766 M 223.21 3.766 L 231.057 44.371 M 223.21 3.766 L 470.833 40.764 L 231.057 44.371 M 231.057 44.371 L 102.886 46.299 M 102.886 46.299 L 469.09 50.829 L 112.477 101.33 M 102.886 46.3 L 112.477 101.33 M 0 117.258 L 13.079 120.278 M 0 117.258 L 26.157 217.406 M 0 117.258 L 112.477 101.33 M 13.079 120.278 L 534.483 57.874 M 13.079 120.278 L 40.979 232 M 534.484 57.874 L 558.026 128.833 M 534.484 57.874 L 534.484 161.041 M 558.026 128.833 L 558.026 166.577 M 558.026 128.833 L 571.976 128.833 M 906.79 3.766 L 898.943 44.371 M 906.79 3.766 L 659.167 40.764 L 898.943 44.371 M 898.943 44.371 L 1027.11 46.299 M 1027.11 46.299 L 660.91 50.829 L 1017.52 101.33 M 1027.11 46.3 L 1017.52 101.33 M 1130 117.258 L 1116.92 120.278 M 1130 117.258 L 1103.84 217.406 M 1130 117.258 L 1017.52 101.33 M 1116.92 120.278 L 595.517 57.874 M 1116.92 120.278 L 1089.02 232 M 595.517 57.874 L 571.975 128.833 M 595.517 57.874 L 595.517 161.041 M 571.975 128.833 L 571.975 166.577" fill="transparent" height="231.99999987792967px" id="epMph3ju2" stroke-dasharray="" stroke-linecap="round" stroke-linejoin="round" stroke-width="1" stroke="rgb(229, 218, 213)" width="1130.0000439453124px"/></svg>)
GLiNER-2 benchmark results
GLiNER-2 delivers strong performance across standard NER benchmarks while remaining fast and efficient in production environments.
![](data:image/svg+xml,<svg display="block" role="presentation" viewBox="0 0 350 148" xmlns="http://www.w3.org/2000/svg"><path d="M 69.061 3.766 L 72.569 2.013 L 165.37 35.731 L 172.654 0 L 176.97 0 L 184.254 35.731 L 277.055 2.013 L 280.562 3.766 M 69.062 3.766 L 71.49 44.371 M 69.062 3.766 L 145.677 40.764 L 71.49 44.37 M 71.49 44.37 L 31.833 46.298 M 31.833 46.298 L 145.137 50.828 L 34.8 101.33 M 31.834 46.3 L 34.802 101.33 M 0 117.258 L 4.047 120.278 M 0 117.258 L 8.093 217.406 M 0 117.258 L 34.8 101.33 M 4.047 120.278 L 165.37 57.874 M 4.047 120.278 L 12.679 232 M 165.37 57.874 L 172.654 128.833 M 165.37 57.874 L 165.37 161.041 M 172.654 128.833 L 172.654 166.577 M 172.654 128.833 L 176.97 128.833 M 280.562 3.766 L 278.134 44.371 M 280.562 3.766 L 203.947 40.764 L 278.134 44.371 M 278.134 44.371 L 317.791 46.299 M 317.791 46.299 L 204.487 50.829 L 314.823 101.33 M 317.791 46.3 L 314.823 101.33 M 349.624 117.258 L 345.577 120.278 M 349.624 117.258 L 341.531 217.406 M 349.624 117.258 L 314.823 101.33 M 345.577 120.278 L 184.254 57.874 M 345.577 120.278 L 336.945 232 M 184.254 57.874 L 176.97 128.833 M 184.254 57.874 L 184.254 161.041 M 176.97 128.833 L 176.97 166.577" fill="transparent" height="231.99999987792967px" id="gALvvd8gn" stroke-dasharray="" stroke-linecap="round" stroke-linejoin="round" stroke-width="1" stroke="rgb(229, 218, 213)" width="349.624005859375px"/></svg>)
EFFICIENCY
GPT-5
GLiNER-M
GLiNER-2-XL
Parameters
–
209M
1B
Hosting
–
Self-host
API
Latency
10000ms+
160ms
130ms
Descriptions
CPU
Privacy
Fine-tuning
Classification
Data structuring
Extract entities, classify text, and generate JSON
from any document in real time.
Join the community
Join our active community on discord
Join now
Need help?
Get in touch with our support team.
Contact Support
Fastino
Fastino (“Fastino”) develops specialized AI models and provides APIs designed to support structured data extraction, classification, reasoning, and production AI workflows. Fastino is a technology company and does not provide legal, financial, compliance, or advisory services.
Any outputs, predictions, classifications, or decisions generated through Fastino models are based on the configuration, data, and implementation provided by the customer. Fastino does not control, verify, or guarantee the accuracy, completeness, or suitability of model outputs for any specific purpose. By using this website or Fastino’s models and services, you acknowledge that all content and outputs are provided for informational and operational purposes only and agree to our Terms of Use and Privacy Policy.
2026 Fastino, Inc.
All rights reserved