Jev directory
CommunityJev Integrations & Adapters
Decisions API
A decision-model marketplace and playground: one POST /v1/systemone endpoint in front of two dozen models including Jev 1.13 and 1.14, with structured answers, probabilities, and a 100-credit starting balance.
- Reading time
- 2 min
- Published by
- Community
- Author
- Decisions API
- Last verified
- Oct 2026
- Languages
- JavaScript
- Capabilities
- Requires API key
Highlights
- Jev 1.13 is listed as typesafe/jev-1.13 with alias jev-latest at 600 credits per million input tokens; upstream $0.042 versus site $0.06.
- Jev 1.14 is listed with a 262,144-token context and up to four PNG, JPEG, or WebP images: 4 MiB each, 8 MiB total, 16 MP each.
- Calls POST https://decisions-api.dev/v1/systemone with a Bearer token; the JS sample checks body.code and reads body.data.result.answers.
- The workbench allows up to eight questions per run, reserves a one-credit budget before calling, and refunds failed calls.
- Task examples include support routing, agent routing, citation verification, content moderation, lead scoring, and LLM guardrail.
Watch out
Third-party aggregation: the hero says browse 24 models while the catalog header says 26, the flagship example is a static illustration the page labels as not a live response or accuracy measure, and Jev routes through OpenRouter at a site price above upstream. Jev 1.14's image input is experimental and header-gated per TypeSafe's danger-zone conventions.
Questions about this entry
Short answers drawn from the linked project or page.
A hosted site for exploring decision models in one place: compare Jev, Liquid d1, Kev, Solar, Tev1, and Span in the playground, then use the API to classify, score, and route text with structured answers and probabilities.
POST https://decisions-api.dev/v1/systemone with a server-side Bearer token and a body carrying model, state, and questions; a choice question names the options and their meanings, and the response returns answers under body.data.result.answers.
Jev 1.13 as typesafe/jev-1.13 with alias jev-latest and Jev 1.14 as typesafe/jev-1.14. Platform price is 600 credits per million input tokens; the page shows upstream $0.042 versus site $0.06 per million input tokens.
A 262,144-token context and up to four PNG, JPEG, or WebP images at 4 MiB each, 8 MiB total, and 16 MP each, returning typed answers with probabilities like the text-only models; treat the image path as experimental rather than production-ready.
New accounts receive 100 credits once, one balance covers playground, API, and evaluation calls at the same per-model rates, a budget is reserved before each call, successful calls settle actual input usage, and failed calls are refunded.
The workbench allows up to eight questions with a one-credit maximum budget for the run and supports text or JSON shared state, with images on vision models; decision models bill input while multimodal chat models bill input and output.
No. The page labels its sample as an illustrative static example and says the values are not a live model response or a measure of accuracy; also, the hero says browse 24 models while the catalog header says 26.
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
Concentrate's beta /v1/decisions endpoint serves TypeSafe's Jev with the same request and response shapes as TypeSafe's System One API and OpenRouter, returning calibrated probabilities for noul, choice, and score questions.
Jev Integrations & AdaptersDocs#community#gateway#api
Community
LiteLLM'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/litellmPythonAlibaba's multi-agent platform, which implements native TypeSafe Jev classification through JevClassifierModel for binary, choice and score routing across agent pipelines. Python 3.11+, Apache-2.0, with a FastAPI agent service and web UI.
Jev Integrations & Adapters#community#multi-agent#framework
Community
agentscope-ai/agentscopePython
agentscope-ai/agentscopePythonCLI-installed Gmail classifier that runs 24/7 on user-owned Google Apps Script: the worker asks Jev for three typed judgments per thread (requires_action, is_important, bucket), applies labels, stars, and optional archiving, and routes ambiguous or low-confidence mail to a Review label.
Jev Integrations & Adapters#community#gmail#email
Community
vynnlee/jev-mailTypeScript
vynnlee/jev-mailTypeScriptA lightweight Jev/System One compatible HTTP gateway that turns an existing SGLang or vLLM deployment into a decision service by scoring candidate tokens: no training, no weight changes, noul/choice/score in and probabilities out.
Jev Integrations & Adapters#community#catalog-import#madewithjev
Community
david-lolly/jev-compatiblePython
david-lolly/jev-compatiblePythonA Google Sheets add-on that classifies, tags and scores text with plain-language formulas: JEV_IF, JEV_PROB, JEV_CHOICE and JEV_SCORE return typed values, and uncertain rows can say UNSURE instead of guessing.
Jev Integrations & Adapters#community#catalog-import#cobanov
Community
cab14bacc/jev-sheetsTypeScript
cab14bacc/jev-sheetsTypeScriptFrom 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.