Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

OneJev1.5-0.8B

OmniJevDecision modelOpen weights

OneJev1.5-0.8B by OmniJev is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 29.0 on the Jev Decision Index (rank 108).

Pricing

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

Specifications

Provider
OmniJev
Parameters
1B
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
Qwen/Qwen3.5-0.8B
Jev-compatible request
Yes
Runs on CPU
Yes
License
apache-2.0
Hugging Face
OmniJev/OneJev1.5-0.8B

Benchmarks

Jev Decision IndexECE 0.035
29.0

Jev Decision Index: public 42.7, ECE 0.035, Brier 0.416. Lower ECE means its probabilities can be taken at face value.

Self-reported by the publisher

The model's own claims, often on its own sets or a self-run copy of a public suite. Not independently verified and never ranked alongside measured results.

Jev Decision Index public suite (self-run)Self-reportedDecision Index public balanced skill, edition 0.3 kit (release-v3), self-run
42.7
jev-decision-index-vision-publicSelf-reported
52.5

Speed & latency

Median latency per call (Decision Index)
83 ms

Compare OneJev1.5-0.8B with…

OneJev1.5-0.8B vs amos-1-large—/1M inOneJev1.5-0.8B vs amos-1-medium—/1M inOneJev1.5-0.8B vs Celeris-1 Decision$0.04/1M inOneJev1.5-0.8B vs ScaleDown Classify-1$0.04/1M inOneJev1.5-0.8B vs Cloudflare clef—/1M inOneJev1.5-0.8B vs Cloudflare clef-flash—/1M in

FAQ

How much does OneJev1.5-0.8B cost?

OneJev1.5-0.8B has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can OneJev1.5-0.8B answer?

OneJev1.5-0.8B answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is OneJev1.5-0.8B well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.035; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is OneJev1.5-0.8B open weight, and can it run on a CPU?

Yes, OneJev1.5-0.8B 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, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.