> ## Documentation Index > Fetch the complete documentation index at: https://docs.fastino.ai/llms.txt > Use this file to discover all available pages before exploring further. # GLiNER > Compare GLiNER2.5, GLiNER2, and GLiNER for efficient information extraction. GLiNER is an open-source family of small language models for efficient information extraction. ## GLiNER2.5 GLiNER2.5 replaces span enumeration with a boundary-prediction architecture. It supports spans of any length within the model context, long-context extraction, joint entity-relation extraction, constrained classification, and span attributes. It remains small and can run without a GPU. * **Unlimited span length** — Extract full addresses, legal references, and other long entities without configuring a maximum span width. * **Constrained classification** — Declare rules across classification tasks to prevent contradictory label combinations. * **Span attributes** — Classify extracted spans by attributes such as sentiment, severity, or negation in the same forward pass. * **Long-context extraction** — Process contracts, reports, and transcripts with a 4,096-word context and chunk longer documents while preserving offsets. * **Joint information extraction** — Extract entities and relations as one schema-constrained graph for knowledge bases and agent memory. ## Compare GLiNER generations | | GLiNER2.5 | GLiNER2 | GLiNER | | --------------------- | --------------------------------------- | ---------------------------------------- | --------------------- | | Architecture | Boundary prediction | Span enumeration | Span enumeration | | Primary use | Constraint-aware structured extraction | Entity extraction and structured parsing | Open-vocabulary NER | | Model sizes | 74M small, 194M base, 287M multilingual | 205M base, 300M multilingual | 50M small, 90M medium | | Input context | 4,096 words | 2,048 tokens | 512 tokens | | Maximum span length | No configured cap | 8 words | 12 words | | Text classification | Yes, with cross-task constraints | Yes | No | | Structured extraction | Yes | Yes | No | | Relation extraction | Yes | Yes | No | | Span attributes | Yes | No | No | GLiNER2.5 is the recommended starting point for new extraction projects. Use GLiNER2 for existing schema-based integrations and the original GLiNER for open-vocabulary NER checkpoints built on the first-generation package. Read about the architecture, benchmarks, and use cases. Browse Fastino models and their model IDs.