Home / Inference APIs / Kev

Kev

Open Source

Open decision models from 0.8B to 27B, built on Qwen and compatible with TypeSafe's Jev API.

Kev is a family of small decision models built on Qwen3.5 and Qwen3.8, in 0.8B, 4B, 9B and 27B sizes. It answers yes/no, multiple-choice and rating questions with calibrated probabilities.

Its server matches TypeSafe's System One API: the TypeSafe Python SDK works against a self-hosted Kev unchanged. You can fine-tune on your own labelled examples and deploy an endpoint that scales to zero when idle. Apache-2.0, by Jared Palmer.

Pricing: Free

Hosting Self-hosted

Pricing Free, Free (open-source)

License APACHE-2.0

Visit website →

Screenshot of Kev webpage

Kev Alternatives

Explore 107 products in the Inference APIs category. View all Kev alternatives.

Laya

Open-source multilingual decision model: typed choices, scores and yes/no answers in one forward pass.

Open Source From Free (open-source)

TypeSafe Jev

Hosted decision model that returns typed choices, scores and yes/no answers with calibrated confidence.

From $0.042 per 1M input tokens

CheapestInference

Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows

From $22/month (Core pool, one daily 8-hour window)

Anyscale

Fast, cost-efficient, serverless APIs for LLM Serving and Fine Tuning

Together AI

The fastest cloud platform for building and running generative AI.

From Pay-per-token

Mistral

Use models in a few clicks with our platform. Download our open models for deep access.

Open Source From $0.10/1M tokens

View all Inference APIs tools ≫

Work on Kev? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →