GLiNER2.5 Multi v1
Text Classificationby Fastino
GLiNER2.5 Multi is a 287M-parameter multilingual information extraction model built on mDeBERTa-v3-base. It supports zero-shot named entity recognition, text classification, and structured JSON extraction across multiple languages, making it well suited for extracting people, organizations, locations, attributes, and other custom entities without task-specific retraining.
Specifications
Parameters
287M
Context length
n/a
Task
Text Classification
Provider
Fastino
Billing
Per token
API
OpenAI-compatible
Pricing
Input
$0.02
per 1M tokens
Output
$0.05
per 1M tokens