← Use cases

Jev and OpenRouter

OpenRouter is a gateway that forwards your prompt to whichever LLM you name. Jev is a different layer: a typed decision model that picks one option and returns it with calibrated confidence. They solve different problems — and Jev is a great way to decide which OpenRouter model to call.

If you came here asking whether Jev is 'on OpenRouter', the useful answer is that Jev isn't just another chat model to proxy — it's TypeSafe AI's System One decision model with its own hosted endpoint. You call it directly for a typed answer: one of your options, a probability for each, and a confidence value, in roughly 70–500ms for about $0.001.

Jev vs OpenRouter

OpenRouterJev
What it isLLM gateway / routerTyped decision model
OutputWhatever the chosen LLM returnsOne typed option + confidence
Use it forSending prompts to many modelsDeciding, classifying, judging
LatencyThe model's latency~70–500ms
CostThe model's price~$0.001 per decision

Use Jev to route across OpenRouter

The two compose. Put Jev in front of your OpenRouter call as the router's brain: define your candidate models as options, send the request as state, and Jev returns the one to use plus a confidence score. Cheap, fast, calibrated model selection — then OpenRouter forwards the actual prompt to the model Jev picked.

Call Jev

POST https://jevtypesafeai.com/api/v1/decide with a jv_live_ key (official upstream POST https://api.typesafe.ai/v1/systemone). The Model Router tool shows this pattern running live.

See also: Model Router (live) · Jev vs an LLM · Jev for AI agents

Route smarter with Jev

Grab a jv_live_ key and pick the right model in one typed, calibrated call.

▶ Try Jev freeGet an API key →
Jev and OpenRouter — typed routing vs an LLM gateway · Jev by TypeSafe AI