cua-s1-4b-0.2
cua-s1-4b-0.2 by cua-ai 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
- cua-ai
- Parameters
- 4B
- Released
- Sep 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/Qwen3.5-4B
- Jev-compatible request
- No
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- cua-ai/cua-s1-4b-0.2
Benchmarks
- DecisionBenchECE 0.114
- 0.523
Compare cua-s1-4b-0.2 with…
FAQ
How much does cua-s1-4b-0.2 cost?
cua-s1-4b-0.2 has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can cua-s1-4b-0.2 answer?
cua-s1-4b-0.2 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is cua-s1-4b-0.2 well calibrated?
No calibration measurement for cua-s1-4b-0.2 is recorded yet.
Is cua-s1-4b-0.2 open weight, and can it run on a CPU?
Yes, cua-s1-4b-0.2 has open weights. It needs a GPU to run at useful speed.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (DecisionBench, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.