Is this TypeSafe's manual or someone's summary of it?

A summary. It is an independent developer reference site, not vendor documentation, and its latency, price and context figures restate what TypeSafe publishes. Treat the numbers as restated vendor claims until you measure them against your own states and question mix.

Does this replace my LLM, or does it just route to one?

Neither replaces nor routes. A request is a state plus a map of typed questions answered as Noul, Choice or Score, with a distribution and a confidence value. There is no generation path, so prose, code and open-ended investigation still belong to a chat model.

Is the confidence field a measured success probability?

The site presents confidence as an explicit training objective meant to be used as a threshold, which is a claim about calibration, not a reported outcome. Nothing on the page says how it was validated or on which labeled set, so measure it yourself before gating on a number.

Which SDKs are official and which are community-maintained?

Python 3.10+ and Node 20+ are the official packages, reading the API key from the environment and defaulting to the latest model. The Rust, Ruby, Go and Elixir clients are community work, so expect to own their compatibility and upgrades.

What are the published latency and price figures on JevAPI.dev?

It lists 70 to 500 ms typical latency, $0.042 per million input tokens with output free, and a 64k token context covering the state plus questions, all restating vendor documentation.

Does JevAPI.dev help me get access to the API?

It repeats TypeSafe's access path: join the early-access waitlist, create a bearer key in the console, then install the official SDK and post a state with typed questions; the site itself grants no access.

What does parallel by design mean for a JevAPI.dev request?

Every question on a state is evaluated in one call, so the reference advises fanning out freely; each answer maps back by key and carries its own distribution and confidence value.

CommunityJev Tools & CLIs

JevAPI.dev

A third-party developer reference for the Jev API: primitives, quickstart curl, SDK pointers, and published latency and pricing figures.

See highlights

Open jevapi.dev

Format: Docs
Published by: Community
Last verified: Sep 2026

Tagscommunity docs api

Works forJev for Classification

Used inJev for Software & DevTools

Platforms: API

Highlights

Documents model jev-latest in early access with POST /v1/systemone.
Lists 70 to 500 ms typical latency, $0.042 per million input tokens, output free.
64k token context for state plus questions; three primitives: Noul, Choice, Score.
Links official Python and Node SDKs and mentions community Rust, Ruby, Go, and Elixir clients.

Watch out

Independent site, not TypeSafe's manual. Figures restate vendor documentation.

Questions about this entry

Short answers drawn from the linked project or page.

Related terms

Glossary definitions related to this entry.

More Jev resources like this

typesafe-jev crate

Rust docs for typesafe-jev 0.2.0, a blocking client that sends one state and a set of Choice, Score, and Noul questions and prices input tokens at list rate.

Jev Tools & CLIsDocs#community#docs#rust

Community

XERJ

3.5k

An Elasticsearch-compatible autoindex search layer that optionally sends top hits to TypeSafe Jev and reorders results by relevance scores.

Jev Tools & CLIs#community#rust#search

Community

xerj-org/xerjRust

Paca

1.9k

A Go-based team workspace with optional Jev AI for agent auto-routing, task auto-fill, auto-assign, and automation condition nodes.

Jev Tools & CLIs#community#go#agents

Community

Paca-AI/pacaGo

GUI JEV Harness

Python harness for GUI grounding: it divides a screenshot into grid tiles, has a vision model describe each tile neutrally, then asks typesafe-ai/jev to choose among the descriptions. Local confidence and margin gates decide whether to descend or refuse, and it emits only a point and bounding box.

Jev Tools & CLIs#community#gui-grounding#computer-use

Community

ZihuaEvan/GUI_JEVPython

omo-jevlike-router

A Jev-style one-pass skill router for OmO agents: a frozen Qwen2.5-0.5B with a tiny option-attention head scores the whole skill catalog per prompt, and an extension shrinks the system prompt to the top-K skills, failing open.

Jev Tools & CLIs#community#routing#skills

Community

islee23520/omo-jevlike-routerPython

jeff

Go CLI for Jev with noul, choice, score, eval, rank, and models commands: rank sends one Score question per item per weighted YAML dimension in a single request and sums weight times score in code, while threshold flags turn a failed gate into exit code 10 for scripts and CI.

Jev Tools & CLIs#community#cli#go

Community

saembit/jeff-cliGo

From the Jev guides

Original write-ups on what this entry is for.

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

Exporting Decision Models: GGUF, ONNX, and Device Runtimes

Oct 10, 2026

Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.

Jev Tools & CLIs#open-models#local#onnx

Read article

Records at Rest: Documents, Inboxes, and Risk Queues

Sep 28, 2026

Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.

Jev Tools & CLIs#classification#email#security

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai