Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking.
The first System One model. Reads a state, answers typed Choice, Score and Noul questions in one call with calibrated probabilities, and generates no text. Closed weights, served by TypeSafe AI.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
jev
Fine-tuned from
qwen/qwen3-8b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
TypeSafe AI
Input price
—
$0.042/MTok
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between clm and jev?
clm is from Contrastive-LM and jev from TypeSafe AI. clm has open weights you can download and run; jev is only available as a hosted API. Both answer choice, score, noul, classify and route questions. Only clm answers rank. clm is licensed apache-2.0; jev, proprietary.
Which is more accurate, clm or jev?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, clm or jev?
clm: Free (open weights). jev: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run clm or jev locally?
clm yes — systemone pull contrastive-lm/clm downloads its weights. The other is only served as a hosted API.
