Jev: understand, compare and test TypeSafe's model

Jev, launched in early access by TypeSafe on September 15, 2026, evaluates questions defined by the application and estimates the probabilities of possible answers. Choice also provides a selected option; Score, a weighted score; Noul, the probability of yes. Code combines these results, applies rules and thresholds, and decides whether to route a ticket, call a tool or request a review. A generative model can then write the response for the person.

My assessment as of September 22, 2026: worth testing, with claims that need qualification. Classification predates Jev. The value of its API depends on errors, cost and latency for a specific task. The sources reviewed establish neither a scientific revolution nor the “scam” allegations. I have not tested the API myself yet.

The full report above brings together the analysis, sources and examples. Both the French and English editions include full-content search, videos linked to the cited moments and code examples you can copy.

Where to start

• Understand how it works: Choice, Score and Noul, followed by the differences between probabilities, confidence and calibration.
• Assess the claims: classifiers, marketing and “scam” allegations, with arguments in favour, criticism and the limits of each.
• Try it in code: install the SDK and send a first ticket. The example covers API keys, errors and precautions before a billable call.

Read the numbers in context

• 70 to 500 ms per call: TypeSafe’s claimed range, dependent on the task and access conditions.
• $0.042 per million input tokens, with free outputs: price checked on September 21, 2026. At 1,000 tokens per request, 100,000 requests would cost $4.20 for Jev alone, excluding retries and other services.
• Roughly 200× faster and 445× cheaper: results from TypeSafe’s launch comparisons, not guaranteed gains for every application.

The report compares those claims with independent tests and explains how to count costs across the whole workflow. A structured response can still be wrong; its format does not remove the need to measure quality.

Inside the report

• 26 chapters and 109 sources covering the API, publicly described architecture, training methods, benchmarks and open alternatives.
• Video analyses, including Theo and Fireship, with timestamped links to demonstrations and criticism.
• Proposed tests for GitHub, Sentry, release notes, YouTube Insights and Paper Insights.
• Diagrams, a glossary and a protocol for comparing Jev with existing rules, classifiers and LLMs with constrained output.

An evolving report

Version 0.15.0 clarifies the distinction between Jev evaluations and application decisions, corrects the responsibility diagrams and adds an offline demonstration of a policy in code. The 4 original infographics remain available in English and French. The report distinguishes TypeSafe’s claims, other authors’ results and my own analysis. The tutorial was checked with the SDK and a mock transport; that does not measure the model’s performance.

The report shows its last update at the top. Its revision history records additions and corrections.

Have a question, a test result or a source to contribute? Contact me on LinkedIn.