GoKawiilTypeSafe AI launches Jev, a decision-focused model claiming 40-400x lower cost than LLMs
TypeSafe AI, founded by former OpenAI researcher Diogo Almeida, has released Jev in early access, a new type of AI model designed to make fast structured decisions rather than generate text. The company says Jev matches existing large language models on decision-making tasks while running 20-200 times faster and 40-400 times cheaper, using a new architecture and a training method called Reinforcement Learning for Calibrated Decisions.
GoKawiil's interpretation of the reporting above, not reported fact.
Most AI investment has gone into conversational chat models, but many real-world automation tasks need quick, reliable structured outputs rather than free-form text, and chat models can be slow, expensive, and prone to hallucination for these uses. If Jev's efficiency and accuracy claims hold up under independent testing, it could open a distinct market for embedding AI directly into software pipelines that need probabilistic decisions rather than conversation.
- TypeSafe AI's Jev model targets structured decision-making instead of text generation, avoiding hallucination by design.
- The company claims 40-400x cost savings and 20-200x speed gains over existing frontier LLMs for these tasks.
- Jev uses a new training approach, RLCD, focused on calibrated probabilistic answers rather than human preference or verifiable rewards.
Source: typesafe.ai, 2026-09-15
Published there as: “Jev: New frontier model 40-400x cheaper and 20-200x faster”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.