Wire flash
TypeSafe AI launches Jev, a small System One decision model with 150ms response time
Editorial responsibility
- No named human review is recorded for this page.
- Source reporting is collected, normalized, translated or condensed automatically when needed.
- Automatically published source-backed update
TypeSafe AI has introduced its first model, named Jev, described as a small and customizable System One decision model. Unlike large language models (LLMs), Jev cannot reason or write explanations; instead, it generates rapid judgments with calibrated probabilities and a confidence score. Complex tasks are broken down into separate questions and recombined in code. TypeSafe reports a response time of approximately 150 milliseconds per call, at around 100 times lower cost and faster responses than LLMs. Pricing is set at $42 per billion input tokens, with free output.
Source report
TypeSafe AI has introduced its first model, named Jev — a small and customizable System One decision model.
Unlike large language models (LLMs), Jev cannot reason or write explanations. Instead, it generates a fast judgment with calibrated probabilities and a confidence score. Any more complex tasks are broken down into separate questions and recombined in code.
Key Performance Metrics
- Response time: Approximately 150ms per call
- Cost efficiency: Around 100x lower cost and faster responses than LLMs
- Pricing: $42 per billion input tokens, with free output
Source
testingcatalogNeutral / independent
Part of this Story
TypeSafe AI launches Jev, claiming 20-200x speed boost over LLMs by skipping token generation