I stayed up til 2am and spent $1,000 benchmarking Jev Router so you don't have to.
Performance on DeepSWE was roughly the same as GPT-6 Astra on low. It costs slightly more, and it took almost 5x longer to run.
Theo - t3.gg
@theo
OpenRouter @OpenRouter
Introducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai
The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Here's how it works 👇🏻
The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Here's how it works 👇🏻
9:12 AM UTC · Sep 26, 2026 · 538K Views
2321183.6K1K
Theo - t3.gg
@theo
Reminder that I love Jev! I use it for a ton of things and I'm super happy with it. It's one of my favorite releases of the year.
I'm just tired of these dumb ideas.
I'm just tired of these dumb ideas.
9:17 AM UTC · Sep 26, 2026 · 38.5K Views
24780229
Theo - t3.gg
@theo
Theo - t3.gg @theo
Reminder that Jev is a "system one" model. It does not reason. It categorizes.
It is nearly impossible to know how "complex" a task is purely from a prompt. You need to understand the system the prompt is made in, the tools the agent has access to, and the complexity of what the
It is nearly impossible to know how "complex" a task is purely from a prompt. You need to understand the system the prompt is made in, the tools the agent has access to, and the complexity of what the
10:21 PM UTC · Sep 26, 2026 · 15.9K Views
306215