TryJev · House #23,648

What it is

Calls itself “decision model”.

• Calls itself: decision model

“A decision model that turns messy input into a clear choice, score, or yes/no — for routing, triage, and high-volume classification.”

Where it puts itself

Rules out “open-ended generation”.

• Says it will not: open-ended generation

“Unlike LLMs, it does not generate text — it returns typed probabilistic answers for the questions you define, built for high-volume classification and routing.”

“Need open-ended generation? Use an LLM.”

What it costs

No free plan. No monthly plan. Prices quoted: $0.042 / 1M tokens.

• Monthly: no
• Free plan: no
• Price: $0.042 / 1M tokens

“Input $0.042 / 1M tokens”

“Input-only pricing at $0.042 / 1M tokens with free output.”

Who it sells to

Sells to businesses. Built for teams. In English.

• Sells to: businesses
• Company size: teams
• Languages: English

“Ideal for support, trust & safety, and ops automation.”

“Where teams use Jev”

How it runs

A API. Hosted in the cloud. Offers an API. AI is the core of the product. You can bring your own API key.

• Kind: api
• Runs where: cloud / hosted
• API: yes
• AI role: core to the product
• Bring your own key: yes

“…curl https://openrouter.ai/api/v1/chat/completions”

“Jev is a model by TypeSafe AI, served via OpenRouter.”

What it works with

Runs inside Jev. Names GPT, GitHub and 2 more on its pages.

• Runs inside: Jev
• Names: GPT · GitHub · OpenRouter · +1

“Every team shipping text classification eventually asks: should this be an LLM call or something smaller and faster? This guide compares Jev vs GPT-class models”

“GitHub”

What it offers as proof

Live, no waitlist. Publishes a blog.

“Blog -> https://tryjev.dev/blog”