Loading comparison…
COMPARE
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 | together-ai/tev1 |
|---|---|---|
| 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. | Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published. |
| Decides | choice, score, noul, classify, extract, route | choice, classify, route |
| Architecture | gliner2 | tev |
| Fine-tuned from | fastino/gliner2-large-v1 | qwen/qwen3.5-4b |
| License | apache-2.0 | Unspecified — weights licence being finalised |
| Availability | Open weights + hosted API | Open weights + hosted API |
| Hosted by | Fastino | Together AI |
| Input price | — | $0.042/MTok |
| Decision accuracy | 60.2% | 88.0% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 38.3 ms | — |
| p95 latency | — | — |
| Evaluation suite | Fastino fast-decisions suite (17 datasets) | Together development set (reused, not held out) |
| Latest version | 2026.09.25 | 2026.09 |
| Variants | encoder_config | — |
| Size of latest version | 1.8 GB | 8.7 GB |
| Files | 6 | 10 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, deberta, extraction, gliner, 340m | system-one, qwen, lora, together, 4b |
| Updated | Sep 26, 2026 | Sep 26, 2026 |