Featherless AI released Simple Jev. It turns any open model into a classifier or Jev endpoint. The server reads next-token logits to build JSON responses. A public demo API is available with no login or key. It supports choice, score, and noul question types. The demo has a 2k-token context limit and 2 RPS rate limit. Production plans offer higher limits. The evaluation framework includes JevBench scoring and text/decision suites. Local deployment requires Python 3.12+, Transformers, and PyTorch. The server reuses KV cache across question batches. It does not generate or parse JSON completions. The API ignores unknown top-level fields. Chat input uses the model's own chat template.
What it unlocks
Running any open model as a classifier or Jev endpoint without a separate classifier head.
- 2k-token context limit
- 2 requests per second
- 477 development/selection decisions
- 1,024 tokens per question (Laya default)
What you need to act on it
- Python 3.12 or newer
- Hugging Face Transformers and PyTorch
- a compatible open model
Sources