Lavoir
Lavoir by Mogan AI is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 4.4 on the Jev Decision Index (rank 151).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- Mogan AI
- Parameters
- 396M
- Released
- Sep 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Score (ordered rubric), Yes / no
- Mechanism
- Encoder classifier
- Backbone
- answerdotai/ModernBERT-large
- Jev-compatible request
- No
- Runs on CPU
- Yes
- License
- cc-by-nc-4.0
- Hugging Face
- moganai/lavoir
Benchmarks
- Jev Decision IndexECE 0.149
- 4.4
Jev Decision Index: public 8.8, ECE 0.149, Brier 0.728. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare Lavoir with…
FAQ
How much does Lavoir cost?
Lavoir has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Lavoir answer?
Lavoir answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Lavoir well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.149; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is Lavoir open weight, and can it run on a CPU?
Yes, Lavoir has open weights. It is small enough to run on a CPU.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Enterprise Decision Arena, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.