All models
COMPARE
Put models side by side.
What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.
| Property | fastino-labs/gliner2-5-decide |
|---|---|
| Summary | Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations. |
| Decides | choice, score, noul, classify, extract, route |
| Architecture | gliner2 |
| Fine-tuned from | fastino/gliner2-large-v1 |
| License | apache-2.0 |
| Availability | Open weights + hosted API |
| Hosted by | Fastino |
| Input price | — |
| Decision accuracy | 60.2% |
| Calibration error | — |
| Valid action rate | — |
| Median latency | 38.3 ms |
| p95 latency | — |
| Evaluation suite | Fastino fast-decisions suite (17 datasets) |
| Latest version | 2026.09.25 |
| Variants | encoder_config |
| Size of latest version | 1.8 GB |
| Files | 6 |
| Downloads | 0 |
| Stars | 0 |
| Tags | system-one, encoder, deberta, extraction, gliner, 340m |
| Updated | Sep 25, 2026 |