Valen-4B
Valen-4B by Valen-Team is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 37.6 on the Jev Decision Index (rank 131).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- Valen-Team
- Parameters
- 5B
- 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/Qwen3.5-4B
- Jev-compatible request
- No
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- Valen-Team/Valen-4B
Benchmarks
- Jev Decision IndexECE 0.107
- 37.6
Jev Decision Index: public 38.5, ECE 0.107, Brier 0.481. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare Valen-4B with…
FAQ
How much does Valen-4B cost?
Valen-4B has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Valen-4B answer?
Valen-4B answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Valen-4B well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.107; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is Valen-4B open weight, and can it run on a CPU?
Yes, Valen-4B has open weights. It needs a GPU to run at useful speed.
Data as of 2026-10-26. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.