Docs
CommunityJev Integrations & Adapters
Jev on OpenCode Zen
OpenCode's Zen gateway serves Jev 1.13 on its own /v1/systemone endpoint with an OpenCode key: jev-1.13 paid and jev-1.13-free for a limited time, documented with noul, choice, and score examples.
- Format
- Docs
- Reading time
- 2 min
- Published by
- Community
- Author
- OpenCode
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Capabilities
- Requires API key
Highlights
- Serves Jev 1.13 at https://opencode.ai/inference/v1/systemone under the model IDs jev-1.13 and jev-1.13-free.
- The docs show a Noul urgency check, a Choice department router, and a Score frustration rubric, answers keyed by question ID.
- Multiple questions in one request are evaluated in parallel, per the page's second example.
- Console is pay-as-you-go with per-request billing; the free Jev ID is a limited-time model and Console stays optional beside OpenCode Go.
- Select it in OpenCode as opencode/jev-1.13 in opencode.jsonc, or call the inference endpoint directly with a Console API key.
Watch out
A gateway listing, not TypeSafe documentation: the page states no Jev licence, latency, or calibration data, and it does not say how requests reach TypeSafe or on whose account. The free ID is limited-time and the model table's Jev rows carry no per-token price of their own.
Questions about this entry
Short answers drawn from the linked project or page.
POST to https://opencode.ai/inference/v1/systemone with your OpenCode Console API key as a bearer token and model jev-1.13, sending a state and typed questions in TypeSafe's System One shape. In OpenCode itself, select the model as opencode/jev-1.13.
Two: Jev 1.13 (jev-1.13) and Jev 1.13 Free (jev-1.13-free), both served from the same /inference/v1/systemone endpoint. The page describes the free ID as a limited-time model.
Three question types: a Noul asking whether a support request is urgent, a Choice routing a damaged-order request to returns, shipping, or billing, and a Score rating customer frustration on Calm, Frustrated, and Very angry.
The page does not say. It documents the endpoint, model IDs, and request shape only, with no statement about hosting, the account behind the calls, or the weights, so treat the listing as a gateway and verify data terms before sending sensitive state.
Console uses pay-as-you-go pricing with per-request billing and prepaid credits; the page's per-1M-token price table does not carry Jev prices, and it lists no rate limits or free tier beyond the limited-time free model ID.
Yes. The examples are plain curl calls against the inference endpoint with a bearer key, so any client that can POST TypeSafe's request shape works, provided it is configured for the opencode.ai base URL rather than TypeSafe's own API.
No. Console is optional and works like any other OpenCode provider; the OpenCode Go subscription is the alternative with included usage. Console itself is reached from the TUI with /connect and /models after you add credits.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev 1.14 is now on OpenRouter
X: Jev lands on the Vercel AI Gateway
X: Jev as an LLM guardrail inside Agentgateway
YouTube: Greg Isenberg and Ryan Vogel on the businesses Jev unlocks, and a path in through the Vercel AI Gateway.
More Jev resources like this
An opencode plugin that turns an agent's small decisions — is this command safe, which tool fits, is this PR ready — into typed Jev questions with calibrated confidences, labelling each answer auto or escalate so the agent knows when to ask for help.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
darwintechlab/openjevJavaScript
darwintechlab/openjevJavaScriptLiteLLM serves decision models on two routes that share one provider list: /v1/decisions for OpenAI-format bodies and /v1/systemone for System One bodies, with Jev available as the typesafe/jev-latest provider.
Jev Integrations & AdaptersDocs#community#litellm#gateway
Community
An OpenCode V2 plugin that asks TypeSafe Jev whether a prompt is deterministic before the LLM reasons, injecting a JEV PRE-ANALYSIS block and temperature 0 for deterministic turns so simple prompts skip chain-of-thought. Jev failures fail open and the session continues normally.
Jev Integrations & Adapters#community#catalog-import#yibie
A session-aware, OpenAI-compatible gateway that routes chat completions across provider pools by cost, quality, and capability rules, optionally asks configured decision providers typed choice questions with a deterministic fallback, and records requests, decisions, and outcomes in SQLite.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
texasoct/jev-gatewayTypeScript
texasoct/jev-gatewayTypeScriptLiteLLM's proxy adds TypeSafe guardrail hooks and a Jev complexity classifier for policy judgments and request routing across 100+ model providers.
Jev Integrations & Adapters#community#python#gateway
Community
BerriAI/litellmPython
BerriAI/litellmPythonMerged PR in the Kilo Code cloud monorepo that replaces its LLM auto-routing classifier with one OpenRouter /systemone Choice request to typesafe/jev-1.13; the PR reports 0.93-0.94 route accuracy on 72 golden cases at roughly $0.00028 per call, with a 250 ms transport-error retry.
Jev Integrations & Adapters#community#routing#coding-agents
Community
Kilo-Org/cloudTypeScript
Kilo-Org/cloudTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.