rei-v1

gnukeithDecision modelOpen weights

rei-v1 by gnukeith 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: gnukeith
Parameters: 272M
Released: Oct 2026
Open weights: Yes
Question types: Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism: Cross-encoder (NLI)
Backbone: google/embeddinggemma-2
Jev-compatible request: No
Runs on CPU: Yes
License: apache-2.0
Hugging Face: gnukeith/rei-v1

Compare rei-v1 with…

rei-v1 vs amos-1-large—/1M in rei-v1 vs amos-1-medium—/1M in rei-v1 vs Celeris-1 Decision$0.04/1M in rei-v1 vs ScaleDown Classify-1$0.04/1M in rei-v1 vs Cloudflare clef—/1M in rei-v1 vs Cloudflare clef-flash—/1M in

FAQ

How much does rei-v1 cost?

rei-v1 has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can rei-v1 answer?

rei-v1 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is rei-v1 well calibrated?

No calibration measurement for rei-v1 is recorded yet.

Is rei-v1 open weight, and can it run on a CPU?

Yes, rei-v1 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 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.