Jev: New frontier model 40-400x cheaper and 20-200x faster
TypeSafe AI launches Jev, an early-access 'System One' model delivering calibrated structured outputs claimed 40-400x faster and cheaper than LLMs.
TypeSafe AI, founded by former OpenAI researcher Diogo Almeida, released its first 'System One Model' called Jev in early access. Jev forgoes string generation and is trained with Reinforcement Learning for Calibrated Decisions (RLCD) to produce type-safe structured values with calibrated probabilities. The company claims 70-500ms response times (40-200x faster), input pricing of $0.042 per million tokens, and free output tokens via a parallel sampling architecture. Target use cases include AI-powered workflows, real-time applications, and verification/guardrail tasks.
- Jev outputs structured typed values with calibrated probabilities, not strings
- Trained with RLCD: Reinforcement Learning for Calibrated Decisions
- Claims 70-500ms responses, 40-200x faster than frontier LLMs
- Input $0.042/MTok with free output tokens via parallel sampling
- Founder Diogo Almeida previously worked on instruction-following research at OpenAI
From the original article
9 min read at typesafe.ai
Models have been superhuman at chat for years, so where is all the automation? This has been my driving question for the last four years. At OpenAI, I helped build the methods that made language models useful at following instructions and talking with people.
By albelfio · typesafe.ai
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.