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

DecisionTune 1.0

DecisionTuneDecision modelOpen weights

DecisionTune 1.0 by DecisionTune is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 16.7 on the Jev Decision Index (rank 129).

Pricing

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

Specifications

Provider
DecisionTune
Parameters
395M
Released
Oct 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
apache-2.0
Hugging Face
decision-tune/decisiontune-1.0

Benchmarks

Jev Decision IndexECE 0.147
16.7

Jev Decision Index: public 28.9, ECE 0.147, Brier 0.603. 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
28.9

Speed & latency

Median latency per call (Decision Index)
14 ms

Compare DecisionTune 1.0 with…

DecisionTune 1.0 vs amos-1-large—/1M inDecisionTune 1.0 vs amos-1-medium—/1M inDecisionTune 1.0 vs Celeris-1 Decision$0.04/1M inDecisionTune 1.0 vs ScaleDown Classify-1$0.04/1M inDecisionTune 1.0 vs Cloudflare clef—/1M inDecisionTune 1.0 vs Cloudflare clef-flash—/1M in

FAQ

How much does DecisionTune 1.0 cost?

DecisionTune 1.0 has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can DecisionTune 1.0 answer?

DecisionTune 1.0 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is DecisionTune 1.0 well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.147; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is DecisionTune 1.0 open weight, and can it run on a CPU?

Yes, DecisionTune 1.0 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.