DECISION & CLASSIFICATION / Convai Innovations
Laya
An open-weight encoder family with English and multilingual checkpoints for short, typed decisions.
ACCESS & CAPABILITIES
How it fits your workflow
CPU or GPU self-hosting, with a Jev-compatible server. This entry covers the downloadable checkpoints; hosted service terms are not verified here.
- Documented judgment types
- Choose an option · Yes / no probability · Rubric score
- Languages
- Separate English and multilingual checkpoints; the publisher reports 100+ languages for the multilingual model.
- Context and input limits
- English checkpoint: 512 tokens. Multilingual: default 1,024, configurable up to 8,192; long-input quality must be tested.
- Jev-compatible interface
- Documented; not an accuracy guarantee
PRICE & PROBABILITIES
Hosted price unverified
No hosted rate verified for this entry. Self-hosting needs compute, capacity and maintenance; downloadable weights do not make inference free.
Interpret the output
Publisher reports calibration training. Select and record the checkpoint, runtime and any fitted temperature before using its probabilities.
Check before choosing
English and multilingual checkpoints have different limits and behavior.
Published short-input latency is hardware-specific. We have not reproduced it or compared Chinese accuracy.
No shared benchmark measured yet
Our accuracy, calibration, p50/p95 latency and cost per thousand decisions are not measured. This is a source-reviewed capability profile. Compare the same task, model version, language, input size and serving setup before ranking results.
Read the selection and evaluation guide →Official sources & version notes
Convai Innovations · Laya model card ↗ Checked 2026-10-05