Featherless launches Simple Jev for text-free classification

Serverless inference provider Featherless released Simple Jev, an open-source library that turns open-source AI models into fast zero-shot classification engines. It returns categorical or binary decisions without generating conversational text, cutting latency and compute; pricing starts at $0.03 per million input tokens with free output tokens.

• Simple Jev is an open-source library for zero-shot classification on open models
• Pricing starts at $0.03 per million input tokens, output tokens are free
• Hosted endpoints add image support on Gemma and Qwen models
• Free public endpoints cap at 2,000 tokens of context and 2 requests per second