TypeSafe AI Releases Jev for Structured Software Decisions
TypeSafe AI released Jev in early access, as detailed in a company blog post. The company describes Jev as its first System One Model, designed to turn unstructured input into typed probabilistic decisions for software.
Unlike language models that generate text one token at a time, Jev produces defined outputs in parallel and assigns probabilities and confidence scores to them. Developers specify the permitted output structure in advance, which the company says prevents type errors and lets applications use responses without parsing generated text.
TypeSafe AI reports response times of 70 ms to 500 ms and a price of $0.042 per million input tokens, with no charge for outputs. Its internal workflow evaluations found Jev was up to 193.6 times faster and 444.6 times cheaper than comparable language models, though the company said these figures likely represent the higher end of expected gains.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Daily AI Brief.
Also, consider following us on social media:
Daily AI Brief
Daily report covering major AI developments and industry news, with both top stories and complete market updates
Market report
2025 Generative AI in Professional Services Report
Thomson Reuters
This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.
Read moreYou may also like
Google Launches Gemini Decisions API for Fast Model Routing and Policy Checks
Unstructured Launches New Transform Document Parsing Models
Thinking Machines releases Inkling 2 Small, with open weights planned for next week
SpeakLeash Releases Bielik 11B v3.1 and Decision Models
OpenAI Details Activation Classifiers for Model Safety
Daily AI Brief: the AI news that matters, in your inbox.