JevLab · House #22,173

What it is

Calls itself “Public routing evaluation lab”.

• Calls itself: Public routing evaluation lab

“Public routing evaluation lab”

Where it puts itself

Rules out “It never executes code search, runs tests, reads documentation, inspects pull requests, or performs any tool actions.”. Publishes a comparison page.

• Says it will not: It never executes code search, runs tests, reads documentation, inspects pull requests, or performs any tool actions.

“Instead of token-by-token generative reasoning, it evaluates unstructured input against declared schemas in milliseconds, returning both a typed routing suggestion and an empirical confidence score.”

“It never executes code search, runs tests, reads documentation, inspects pull requests, or performs any tool actions.”

What it costs

No monthly plan.

• Monthly: no

“Proprietary ($0.042/1M tokens) + Zero infra setup; 1K–10K context”

Who it sells to

Sells to developers.

• Sells to: developers

“Download a complete, runnable TypeScript routing module with pinned model versions, runtime schema validation, and fail-closed error handling.”

How it runs

A API. Runs locally and works offline. Offers an API. AI is the core of the product. You can bring your own API key.

• Kind: api
• Runs where: on the device, offline
• API: yes
• AI role: core to the product
• Bring your own key: yes

“Download a complete, runnable TypeScript routing module with pinned model versions, runtime schema validation, and fail-closed error handling.”

“Data is stored in IndexedDB on this device.”

What it works with

Names Laya, ModernBERT and 4 more on its pages.

• Names: Laya · ModernBERT · Qwen · +3

“JevLab”

“Laya”

What it offers as proof

Live, no waitlist. Publishes docs and a blog.

“Live evaluation paused”

“Docs -> https://jevlab.dev/docs”