---
title: "TypeSafe AI scales Jev to trillions of tokens in three days on Modal"
description: "TypeSafe AI’s Jev is a System One Model that outputs structured decisions with probabilities rather than generating text, taking state and questions as input and returning typed values. It uses a custom architecture, a parallel sampler for maximum efficiency, and a training method called Reinforcement Learning for Calibrated Decisions (RLCD). Unlike autoregressive LLMs, Jev produces outputs in parallel, enabling low-latency responses suitable for workloads like large-scale automation, fast browser use, and generative user interfaces. Launched on a Thursday, Jev topped OpenRouter’s leaderboard for contexts between 1K and 10K tokens one week later, handling 15.1% of requests on that platform. To meet demand exceeding one trillion tokens in three days, TypeSafe used Modal’s serverless platform for bursty, high-concurrency inference without managing their own infrastructure, gaining control over networking, routing, and autoscaling needed for ultra-low-latency serving."
---

# TypeSafe AI scales Jev to trillions of tokens in three days on Modal

[Modal](https://yomu.fyi/company/modal) · Oct 5, 2026

**Type:** Announcement

## Summary

TypeSafe AI’s Jev is a System One Model that outputs structured decisions with probabilities rather than generating text, taking state and questions as input and returning typed values. It uses a custom architecture, a parallel sampler for maximum efficiency, and a training method called Reinforcement Learning for Calibrated Decisions (RLCD). Unlike autoregressive LLMs, Jev produces outputs in parallel, enabling low-latency responses suitable for workloads like large-scale automation, fast browser use, and generative user interfaces. Launched on a Thursday, Jev topped OpenRouter’s leaderboard for contexts between 1K and 10K tokens one week later, handling 15.1% of requests on that platform. To meet demand exceeding one trillion tokens in three days, TypeSafe used Modal’s serverless platform for bursty, high-concurrency inference without managing their own infrastructure, gaining control over networking, routing, and autoscaling needed for ultra-low-latency serving.

## Context

TypeSafe AI launched Jev, a System One Model for structured decisions, and scaled to over one trillion tokens in three days using Modal’s serverless infrastructure.

## Approach / What changed

TypeSafe AI used Modal’s serverless platform to train, deploy, and scale Jev, handling bursty demand with autoscaling and full stack control without managing infrastructure.

## Takeaways

- Jev is a System One Model that outputs structured decisions with probabilities in parallel, not autoregressive text generation.
- Jev topped OpenRouter’s leaderboard for 1K-10K token contexts one week after launch, handling 15.1% of requests.
- Modal served over one trillion tokens for Jev within three days of launch using serverless infrastructure with autoscaling.

## FAQ

### What is Jev?

Jev is a System One Model that takes state and questions as input and outputs typed structured values with probabilities, using parallel generation instead of autoregressive text.

### How did TypeSafe scale Jev to trillions of tokens?

They used Modal's serverless platform for bursty, high-concurrency inference, gaining control over networking, routing, and autoscaling without managing infrastructure.

### What makes Jev different from LLMs?

Jev is not autoregressive and does not generate text; it outputs structured decisions with probabilities in parallel, focusing on fast, intuitive decisions rather than generalized intelligence.

**Tags:** [AI](https://yomu.fyi/topic/ai), [Inference](https://yomu.fyi/topic/inference), [Modal](https://yomu.fyi/topic/modal), [Serverless](https://yomu.fyi/topic/serverless)

- Source: [Modal](https://modal.com/blog/typesafeai-case-study)
- Source URL: https://modal.com/blog/typesafeai-case-study
- Ingested by Yomu: 2026-10-07T03:00:11.044Z

[Read original post](https://modal.com/blog/typesafeai-case-study)