lev-350m

Franck VerrotDecision modelOpen weights

lev-350m by Franck Verrot is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider: Franck Verrot
Parameters: —
Released: Oct 2026
Open weights: Yes
Question types: Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism: Decoder LM with a decision readout
Backbone: —
Jev-compatible request: Yes
Runs on CPU: —
License: —

Benchmarks

Benchmark Heaven JevBench (Capability): 43.4

Compare lev-350m with…

lev-350m vs amos-1-large—/1M in lev-350m vs amos-1-medium—/1M in lev-350m vs Celeris-1 Decision$0.04/1M in lev-350m vs ScaleDown Classify-1$0.04/1M in lev-350m vs Cloudflare clef—/1M in lev-350m vs Cloudflare clef-flash—/1M in

FAQ

How much does lev-350m cost?

lev-350m has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can lev-350m answer?

lev-350m answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is lev-350m well calibrated?

No calibration measurement for lev-350m is recorded yet.

Is lev-350m open weight, and can it run on a CPU?

Yes, lev-350m has open weights.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Benchmark Heaven JevBench). Pricing is per 1M tokens (USD); confirm with the provider before production use.