# JevModel

> Independent hosted playground, decision flows, batch processing and API for TypeSafe AI’s Jev decision model, with English and Chinese guides. JevModel is not affiliated with TypeSafe AI.

## What it does

Jev turns text or JSON state into typed judgments. Choice selects among named options, Score returns a possibly fractional value on an ordered rubric, and Noul returns a 0–1 probability for a true/false proposition. Applications must set their own action thresholds.

The Console manages saved decision flows, API keys, run history and token balance. Decision Flows run on the token balance (signup tokens included); free accounts can save one flow and any purchase unlocks unlimited flows. Each visited question uses actual input tokens, and completed nodes remain charged if a later node fails. External actions belong to the calling application. Custom questions and criteria do not train or fine-tune a model.

Batch processing accepts CSV, TXT or JSONL, up to 2 MB and 1,000 rows, and exports results for your own evaluation. The service accepts text or JSON; provide existing captions or OCR text for image-related tasks. Probabilities are not correctness guarantees.

## Request shape

`POST /api/v1/systemone` accepts `{ "state": string | object | array, "questions": { "id": { "type": "choice" | "score" | "noul", "instructions": string, "criteria": ... } } }`. Choice criteria are a map of named options, Score criteria are an ordered array of levels, and Noul criteria contain `true` and `false` descriptions. Send 1–8 questions with stable lowercase IDs.

```json
{"state":"The customer was charged twice and requests a refund.","questions":{"escalate":{"type":"noul","instructions":"Should a human billing specialist review this request now?","criteria":{"true":"A specialist should review it now.","false":"No immediate review is needed."}}}}
```

Visitors can run the homepage demo 3 times per UTC day without an account. Create an API key after email verification and send it as `Authorization: Bearer <key>`. Verified accounts get 100,000 free tokens once, shared by the playground, batch processing, Decision Flows and API, subject to site capacity. Free accounts can save 1 Decision Flow and upload 50-row batches; any purchase unlocks unlimited Flows and 1,000-row batches. Token packs start at $4.90 and never expire; unused subscription tokens roll over; yearly plans are 50% off with all 12 months of tokens delivered up front. Console and account pages require sign-in and are excluded from indexing.

## Pages

- [Runnable API examples on GitHub](https://github.com/SouthCat196/jevmodel-examples): Independent JevModel Node.js, Python and curl examples for Choice, Score and Noul. Offline fixtures by default; --live explicitly opts into an API call. MIT example code, not Jev model weights or an official TypeSafe SDK.
- [Home](https://jevmodel.app/)
- [中文首页](https://jevmodel.app/zh)
- [Jev playground](https://jevmodel.app/jev-playground): run the Jev model in the browser, one run without signup
- [Jev API](https://jevmodel.app/jev-api): endpoint, quickstart, pricing and limits
- [Workbench examples](https://jevmodel.app/workbench)
- [Batch processing](https://jevmodel.app/batch)
- [Decision flows](https://jevmodel.app/#flows)
- [Use cases](https://jevmodel.app/use-cases)
- [Guides](https://jevmodel.app/guides)
- [API guide](https://jevmodel.app/guides/api)
- [Usage rules](https://jevmodel.app/pricing)
- [Full guide text](https://jevmodel.app/llms-full.txt)

## Guides

- [How to use Jev: a step-by-step guide](https://jevmodel.app/guides/how-to-use-jev): Learn how to use the Jev model: try it in the playground, write Choice, Score and Noul questions, read probabilities, then call the Jev API and run batches.
- [Jev 怎么用：分步教程](https://jevmodel.app/zh/guides/how-to-use-jev): 学会使用 Jev 模型：在 Playground 试用，编写 Choice、Score、Noul 问题，读懂概率，再调用 Jev API 并批量处理。
- [Jev prompt and question examples](https://jevmodel.app/guides/jev-prompt-examples): Copy working Jev question examples for routing, lead scoring, escalation and moderation. Each example is valid JSON for the Jev playground and API.
- [Jev 提示词与问题示例](https://jevmodel.app/zh/guides/jev-prompt-examples): 可直接复制的 Jev 问题示例，覆盖客服分流、线索评分、升级判断与内容审核，每个示例都是可用于 Jev Playground 和 API 的合法 JSON。
- [JevModel vs the official Jev playground](https://jevmodel.app/guides/jevmodel-vs-official-jev-playground): Compare the TypeSafe console playground with JevModel, an independent Jev playground: model, account, free usage, API, batch, flows and billing.
- [JevModel 与官方 Jev Playground 对比](https://jevmodel.app/zh/guides/jevmodel-vs-official-jev-playground): 对比 TypeSafe 官方 Console Playground 与独立的 JevModel Playground：模型、账号、免费额度、API、批处理、决策 Flow 与计费。
- [Structured Decision Models for Autonomous Agents](https://jevmodel.app/guides/structured-decision-models): Design bounded agent decisions with Choice, Score and Noul. Compare hosted Jev and visual Valen, connect Codex, and evaluate errors, latency and cost.
- [自主 Agent 的结构化决策模型指南](https://jevmodel.app/zh/guides/structured-decision-models): 如何把 Agent 的下一步动作变成可评估的结构化判断？了解 Choice、Score、Noul，比较托管 Jev 与视觉 Valen，接入 Codex，并评估错误、延迟和成本。
- [Valen vs Jev in 2026: Which Decision Model Fits Your Agent?](https://jevmodel.app/guides/valen-vs-jev): Compare Valen and Jev for agent decisions: visual inputs, open weights, published Sokoban benchmarks, self-hosting steps and the limits of each approach.
- [Valen 与 Jev 对比（2026）：你的 Agent 该选哪种决策模型？](https://jevmodel.app/zh/guides/valen-vs-jev): Valen（万澜）与 Jev 有什么关系，Agent 应该怎么选？对比视觉输入、开放权重、作者公布的推箱子评测、自行部署步骤及成本，区分演示成绩与实际生产表现。
- [What is JevModel, and how is it related to Jev?](https://jevmodel.app/guides/what-is-jevmodel): JevModel is an independent Jev playground and API that calls the real typesafe/jev-1.13 model. Learn what it adds, what it costs, how data is handled and when to use the official TypeSafe console instead.
- [JevModel 是什么？与 Jev 有什么关系？](https://jevmodel.app/zh/guides/what-is-jevmodel): JevModel 是调用真实 typesafe/jev-1.13 模型的独立 Jev Playground 与 API。了解它额外提供什么、怎么收费、数据如何处理，以及什么时候应改用 TypeSafe 官方 Console。
- [How to classify text with the JevModel API](https://jevmodel.app/guides/text-classification-api): Classify text into your own labels with a Choice request. See the input, illustrative response, error handling and human-review path.
- [如何用 JevModel API 分类文本](https://jevmodel.app/zh/guides/text-classification-api): 用 Choice 请求把文本归入自定义标签；查看输入、示意响应、错误处理与人工复核路径。
- [Jev probability, confidence and human-review thresholds](https://jevmodel.app/guides/confidence-and-abstention): Understand Choice confidence, Noul probability and Score rubrics. Evaluate thresholds on labeled data before automating a decision.
- [Jev 概率、置信度与人工复核阈值](https://jevmodel.app/zh/guides/confidence-and-abstention): 区分 Choice 置信度、Noul 概率与 Score 量表；在自动化决策前，用标注数据评估阈值。
- [Jev vs embeddings and zero-shot classifiers](https://jevmodel.app/guides/jev-vs-embeddings): Compare typed decisions, vector similarity and zero-shot label scoring for text classification. Choose using your own data and deployment constraints.
- [Jev、Embeddings 与零样本分类器如何选型](https://jevmodel.app/zh/guides/jev-vs-embeddings): 比较类型化判断、向量相似度与零样本标签评分；依据实际数据和部署约束选择文本分类方案。
- [Clef vs Jev: choosing a decision model for your workflow](https://jevmodel.app/guides/clef-vs-jev): Compare Cloudflare Clef with hosted Jev by input needs, API boundaries and deployment. Use a task-specific evaluation before changing your decision layer.
- [Clef vs Jev：如何为实际工作流选择决策模型](https://jevmodel.app/zh/guides/clef-vs-jev): 按输入需求、API 边界和部署方式比较 Cloudflare Clef 与托管 Jev；区分厂商成绩与实际工作流表现，了解替换前应验证哪些条件。
- [Cloudflare Clef and Clef-flash: a practical integration guide](https://jevmodel.app/guides/cloudflare-clef): Learn how Cloudflare Clef takes typed questions, where to call its API, and what to validate before using its answers in an agent or review workflow.
- [Cloudflare Clef 与 Clef-flash：接入与验证指南](https://jevmodel.app/zh/guides/cloudflare-clef): 了解 Cloudflare Clef 的类型化问题、真实 API 路径、输入限制和部署选择；在将答案接入 Agent 或复核流程前验证协议与安全边界。
- [Strands Decider 2B: what it does and how to compare it with Jev](https://jevmodel.app/guides/strands-decider-2b): Understand AWS Strands Labs’ experimental open decision model, checkpoint versions, local serving and a practical Jev evaluation plan.
- [Strands Decider 2B：能力、部署与 Jev 对比](https://jevmodel.app/zh/guides/strands-decider-2b): 了解 AWS Strands Labs 的实验性开放决策模型、checkpoint 版本、本地服务与 Jev 对照评估方法。
- [OpenAI Decisions API vs Jev: contracts, costs and migration](https://jevmodel.app/guides/openai-decisions-api-vs-jev): Compare OpenAI’s public-beta Decisions API with Jev: predicate, choice and score outputs, JSON shapes, refusal handling and a migration checklist.
- [OpenAI Decisions API 与 Jev：接口、成本与迁移](https://jevmodel.app/zh/guides/openai-decisions-api-vs-jev): 对比 OpenAI 公开测试的 Decisions API 与 Jev：predicate、choice、score 输出、JSON 结构、拒答处理与迁移检查。
- [Zero-Shot Text Classification in 2026: LLM Prompts vs Hugging Face vs a Typed API](https://jevmodel.app/guides/zero-shot-text-classification): Compare LLM prompt classification, Hugging Face NLI zero-shot, and a typed Jev API on cost, output stability and confidence. Treat vendor tests as leads, then measure your labels.
- [2026 年零样本文本分类：LLM 提示词、Hugging Face 与类型化 API 怎么选](https://jevmodel.app/zh/guides/zero-shot-text-classification): 对比 LLM 提示词分类、Hugging Face NLI 零样本与类型化 Jev API 的成本、输出稳定性与置信度；把厂商测试当线索，再用自己的标签实测。
- [Zendesk AI Ticket Classification & Routing: Built-in Intelligent Triage vs a Custom Classifier](https://jevmodel.app/guides/zendesk-ai-ticket-classification): Decide when Zendesk Intelligent Triage is enough for topic, sentiment and language, and when to webhook a custom classifier like Jev for your own labels, confidence thresholds and human handoff.
- [Zendesk AI 工单分类与分流：内置 Intelligent Triage 与自定义分类器怎么选](https://jevmodel.app/zh/guides/zendesk-ai-ticket-classification): 判断何时 Zendesk Intelligent Triage 的主题、情绪与语言分类已够用，何时应通过 webhook 接入自定义分类器（如 Jev）以使用自有标签、置信度阈值与人工交接。
- [n8n Text Classifier Node: Built-in vs Calling Jev from a Workflow](https://jevmodel.app/guides/n8n-text-classifier): Compare n8n’s built-in Text Classifier node with an HTTP call to Jev for typed labels, confidence thresholds and human-review branches in support triage workflows.
- [n8n Text Classifier 节点：内置分类 vs 在工作流中调用 Jev](https://jevmodel.app/zh/guides/n8n-text-classifier): 对比 n8n 内置 Text Classifier 节点与通过 HTTP 调用 Jev：类型化标签、置信度阈值与人工复核分支，适合物服分流工作流。
- [Is Jev a Multimodal / Downloadable Model? What JevModel Actually Is](https://jevmodel.app/guides/is-jev-multimodal-model): JevModel is a hosted text/JSON decision API (OpenRouter typesafe/jev-1.13)—not a multimodal, downloadable, or train-your-own model. Clear answers on context limits, Laya/Omni, login and credits.
- [Jev 是多模态 / 可下载模型吗？JevModel 实际是什么](https://jevmodel.app/zh/guides/is-jev-multimodal-model): JevModel 是托管的文本/JSON 决策 API（OpenRouter typesafe/jev-1.13）——不是多模态、可下载或自训模型。澄清上下文上限、Laya/Omni、登录与额度。
- [Intent Classification for Product & Support Text: Rules, LLMs, and Typed APIs](https://jevmodel.app/guides/intent-classification): Compare rules, LLM prompts, and typed decision APIs for product and support intent classification—labels, regression tests, confidence thresholds, and buying-intent edges.
- [产品与客服文本的意图分类：规则、LLM 与类型化 API](https://jevmodel.app/zh/guides/intent-classification): 对比规则、LLM 提示与类型化决策 API 在产品/客服意图分类中的用法：标签、回归测试、置信度阈值与购买意图边界。
- [Sentiment Analysis API in 2026: Cloud APIs vs LLM Prompts vs a Typed Decision Model](https://jevmodel.app/guides/sentiment-analysis-api): Compare cloud sentiment APIs, LLM prompt scoring, and typed Jev Choice/Score for custom aspect labels and abstention—plus when each fits Python-centric pipelines.
- [2026 年的情感分析 API：云 API vs LLM 提示 vs 类型化决策模型](https://jevmodel.app/zh/guides/sentiment-analysis-api): 对比云情感 API、LLM 提示打分与类型化 Jev Choice/Score（自定义方面标签与弃权），并说明何时适合以 Python 为主的流水线。
- [Email Classification with AI: Rules, LLM Prompts, or a Typed Decision API for Inbound Mail](https://jevmodel.app/guides/email-classification): Route inbound email to support, sales, billing, vendor, or low-value queues: how to trim threads and signatures, compare rules, LLM prompts and typed APIs, and send the mid-band to people.
- [用 AI 做邮件分类：入站邮件该用规则、LLM 提示还是类型化决策 API](https://jevmodel.app/zh/guides/email-classification): 把入站邮件分到客服、销售、账单、供应商或低价值队列：如何裁剪线程与签名、对比规则/LLM 提示/类型化 API，并把中间置信带交给人工。
- [LLM-as-a-Judge: Free-Form Prompts, Rubric Scoring, or a Typed Judge with Abstention](https://jevmodel.app/guides/llm-as-a-judge): How to use an LLM as a judge for AI outputs: free-form prompts vs rubric scores vs typed Score and yes/no judges, position and verbosity bias, calibration against human labels, and when not to use a judge.
- [LLM-as-a-Judge：自由格式提示、量表评分，还是带弃权的类型化评审](https://jevmodel.app/zh/guides/llm-as-a-judge): 如何用 LLM 评审 AI 输出：自由提示 vs 量表打分 vs 类型化 Score 与是/否评审，位置偏差与冗长偏差，用人工标签校准，以及何时不该用评审模型。
- [Zapier Text Classification: AI by Zapier Classify vs Vertex Classify Text vs HTTP → Jev](https://jevmodel.app/guides/zapier-text-classification): Compare Zapier’s AI by Zapier Classify prompt template and Google Vertex AI Classify Text with an HTTP call to JevModel for typed Choice/Score/Noul labels, confidence thresholds, and human-review branches.
- [Zapier 文本分类：AI by Zapier Classify vs Vertex Classify Text vs HTTP → Jev](https://jevmodel.app/zh/guides/zapier-text-classification): 对比 Zapier 的 AI by Zapier Classify 提示模板与 Google Vertex AI Classify Text，以及通过 HTTP 调用 JevModel：类型化 Choice/Score/Noul、置信度阈值与人工复核分支。
- [Make.com Categorize Text: AI Toolkit vs HTTP → Jev for Typed Labels and Confidence Thresholds](https://jevmodel.app/guides/make-categorize-text): Compare Make AI Toolkit’s Categorize Text module (name+description categories, optional explanation, single vs multi) with an HTTP call to JevModel for Choice/Score/Noul, confidence thresholds, Router branches, and human review.
- [Make.com Categorize Text：AI Toolkit vs HTTP → Jev（类型化标签与置信度阈值）](https://jevmodel.app/zh/guides/make-categorize-text): 对比 Make AI Toolkit 的 Categorize Text 模块（名称+描述类别、可选解释、单选/多选）与通过 HTTP 调用 JevModel：Choice/Score/Noul、置信度阈值、Router 分支与人工复核。
- [Power Automate Text Classification: AI Builder Category Models vs HTTP → Jev](https://jevmodel.app/guides/power-automate-text-classification): Compare Microsoft Power Automate AI Builder custom and prebuilt category classification with an HTTP connector call to JevModel for typed Choice/Score/Noul labels, confidence thresholds, and human-review branches.
- [Power Automate 文本分类：AI Builder 类别模型 vs HTTP → Jev](https://jevmodel.app/zh/guides/power-automate-text-classification): 对比 Microsoft Power Automate AI Builder 的自定义与预构建类别分类，以及通过 HTTP 连接器调用 JevModel：类型化 Choice/Score/Noul、置信度阈值与人工复核分支。
- [Pipedream Text Classification: Hugging Face Action vs HTTP → Jev for Typed Labels](https://jevmodel.app/guides/pipedream-text-classification): Compare Pipedream’s Hugging Face Text Classification action (modelId, text, optional candidate_labels) with an awaited HTTP/axios POST to JevModel for typed Choice/Score/Noul, branching, and human review.
- [Pipedream 文本分类：Hugging Face 动作 vs HTTP → Jev（类型化标签）](https://jevmodel.app/zh/guides/pipedream-text-classification): 对比 Pipedream 的 Hugging Face Text Classification 动作（modelId、text、可选 candidate_labels）与通过 await 的 HTTP/axios POST 调用 JevModel：类型化 Choice/Score/Noul、分支与人工复核。
- [Google Sheets Text Classification: the =AI() Function vs Apps Script → Jev API](https://jevmodel.app/guides/google-sheets-text-classification): Label spreadsheet rows with the Google Sheets AI function or an Apps Script call to JevModel: fixed Choice labels with probabilities, a review column, Apps Script quotas, and when a CSV upload to Console → Batch is simpler.
- [Google Sheets 文本分类：=AI() 函数 vs Apps Script 调用 Jev API](https://jevmodel.app/zh/guides/google-sheets-text-classification): 用 Google Sheets 的 AI 函数，或用 Apps Script 调用 JevModel，给表格行打标签：固定 Choice 标签与概率、复核列、Apps Script 配额，以及何时直接把 CSV 传到 Console → Batch 更省事。
- [Spam Detection API for Forms and Comments: Turnstile, Akismet, or a Jev Decision Layer](https://jevmodel.app/guides/spam-detection-api): Where a challenge (Cloudflare Turnstile), a spam-reputation service (Akismet), and a typed Jev Choice/Noul check each fit against contact-form, comment, and signup spam, with a quarantine queue instead of silent deletes.
- [表单与评论的垃圾内容检测 API：Turnstile、Akismet 还是 Jev 判断层](https://jevmodel.app/zh/guides/spam-detection-api): 面对联系表单、评论和注册垃圾内容，挑战验证（Cloudflare Turnstile）、垃圾信誉服务（Akismet）与类型化 Jev Choice/Noul 判断各自该放在哪一层；用隔离队列代替静默删除。
- [Slack Message Classification: Route Channel Messages with the Events API and Jev](https://jevmodel.app/guides/slack-message-classification): Classify messages in a Slack help or feedback channel with a small Slack app: receive message.channels events, verify the signature, acknowledge within 3 seconds, then ask Jev a fixed Choice plus an urgency Noul and react, reply, or forward. Includes retries, deduplication, privacy, and when a no-code tool is enough.
- [Slack 消息分类：用 Events API 和 Jev 给频道消息分流](https://jevmodel.app/zh/guides/slack-message-classification): 用一个小型 Slack 应用给求助或反馈频道的消息分类：接收 message.channels 事件、校验签名、3 秒内确认，再向 Jev 提一个固定 Choice 和一个紧急程度 Noul，然后加表情、回帖或转发。包含重试、去重、隐私，以及何时用无代码工具就够。
- [Auto-Label GitHub Issues with AI: a GitHub Actions Workflow That Calls Jev](https://jevmodel.app/guides/github-issue-labeling): Label new GitHub issues as bug, enhancement, question, or documentation with a GitHub Actions workflow that sends the title and body to JevModel and applies one label with gh. Covers the issues trigger, permissions, script-injection safety, an allowlist, a needs-triage fallback, and how to test on closed issues first.
- [用 AI 自动给 GitHub Issue 打标签：调用 Jev 的 GitHub Actions 工作流](https://jevmodel.app/zh/guides/github-issue-labeling): 用 GitHub Actions 工作流把新 Issue 的标题和正文发给 JevModel，再用 gh 打上 bug、enhancement、question 或 documentation 中的一个标签。涵盖 issues 触发器、权限、防脚本注入、标签白名单、needs-triage 兜底，以及如何先在已关闭的 Issue 上测试。
- [Customer Feedback Classification: One Theme, a Priority Score, and Why Sentiment Is Not Enough](https://jevmodel.app/guides/customer-feedback-classification): Sort open-ended NPS comments, reviews, and in-app feedback into one theme plus a follow-up priority. Compare keyword rules, LLM prompts, and a typed Choice plus Score request, and send mixed comments to people.
- [用户反馈分类：一个主题、一个优先级，以及为什么情感分析不够](https://jevmodel.app/zh/guides/customer-feedback-classification): 把 NPS 开放题、评价和应用内反馈分成一个主题加一个跟进优先级。对比关键词规则、LLM 提示和类型化的 Choice 加 Score，并把混合评论交给人。
- [Multi-Label Text Classification: One Choice, Several Yes/No Questions, or a Second Pass](https://jevmodel.app/guides/multi-label-text-classification): When one text belongs to several classes, compare a single Choice, up to eight Noul questions, a second request, and a generative label list. JevModel Choice returns exactly one label.
- [多标签文本分类：一次 Choice、多道是否题，还是第二轮请求](https://jevmodel.app/zh/guides/multi-label-text-classification): 当一段文本同时属于多个类别时，比较单个 Choice、最多八道 Noul、第二次请求，以及生成式标签列表。JevModel 的 Choice 只返回一个标签。
- [Use Jev in Codex with the Official TypeSafe Skill](https://jevmodel.app/guides/codex-jev): Install the official TypeSafe skill in Codex, configure TYPESAFE_API_KEY, and ask Jev to select a next action with a verified API call.
- [Codex 接入 Jev：官方 TypeSafe Skill 教程](https://jevmodel.app/zh/guides/codex-jev): 在 Codex 安装官方 TypeSafe Skill、配置 TYPESAFE_API_KEY，并通过真实 Jev API 调用选择下一步动作，包含完整提示词、验证和排错步骤。
- [What is the Jev model?](https://jevmodel.app/guides/what-is-jev): Understand TypeSafe AI’s Jev decision model, its Choice, Score and Noul outputs, and when to use it.
- [Jev 模型是什么？](https://jevmodel.app/zh/guides/what-is-jev): 了解 TypeSafe AI 的 Jev 判断模型、Choice、Score、Noul 输出及适用场景。
- [Your first Jev decision](https://jevmodel.app/guides/getting-started): Try a support-routing example, read its Choice probabilities, and find your next steps for the JevModel API.
- [第一次运行 Jev 判断](https://jevmodel.app/zh/guides/getting-started): 用客服分流示例运行 Jev 判断、阅读 Choice 概率，并了解后续 API 接入方式。
- [JevModel API: request and response](https://jevmodel.app/guides/api): Use a JevModel API key to send typed Jev questions to /api/v1/systemone.
- [JevModel API：请求与响应](https://jevmodel.app/zh/guides/api): 使用 JevModel API 密钥，通过 /api/v1/systemone 发送类型化判断问题。
- [Choice, Score, and Noul](https://jevmodel.app/guides/question-types): Pick the answer type that matches the decision your code will make.
- [Choice、Score 与 Noul](https://jevmodel.app/zh/guides/question-types): 按照代码需要的结果，选择合适的问题类型。
- [Where typed decisions help](https://jevmodel.app/guides/use-cases): Five starter workflows, from support routing to agent control.
- [类型化判断适合哪些场景](https://jevmodel.app/zh/guides/use-cases): 从客服分流到 Agent 控制，了解五个入门流程。
- [Route customer support with Jev](https://jevmodel.app/guides/support-triage): Classify a message and decide when a person should take over.
- [用 Jev 进行客服分流](https://jevmodel.app/zh/guides/support-triage): 分类客户消息，并判断何时交给人工。
- [Use Jev for review queues](https://jevmodel.app/guides/content-moderation): Triage posts for review without treating a probability as a final verdict.
- [用 Jev 辅助内容审核](https://jevmodel.app/zh/guides/content-moderation): 用概率安排复核，不把概率当作最终裁决。
- [Score leads on a useful rubric](https://jevmodel.app/guides/lead-scoring): Make sales prioritization easier to test and revise.
- [用清晰量表评估线索](https://jevmodel.app/zh/guides/lead-scoring): 让销售优先级更容易检验与修订。
- [Check a claim against evidence](https://jevmodel.app/guides/evidence-checking): Use a narrow proposition to spot unsupported statements.
- [核验主张与证据](https://jevmodel.app/zh/guides/evidence-checking): 用范围明确的命题识别缺乏支持的表述。
- [Route an agent’s next step](https://jevmodel.app/guides/agent-routing): Choose between search, calculation, response, and clarification.
- [为 Agent 选择下一步](https://jevmodel.app/zh/guides/agent-routing): 在检索、计算、回答与追问之间选择。
- [Add a decision gate before tool use](https://jevmodel.app/guides/tool-guardrails): Combine a model signal with deterministic permission checks.
- [在工具调用前增加判断关口](https://jevmodel.app/zh/guides/tool-guardrails): 将模型信号与确定性的权限校验结合。
- [Choose what context to keep](https://jevmodel.app/guides/context-compaction): Use typed questions before trimming a long agent history.
- [判断应保留哪些上下文](https://jevmodel.app/zh/guides/context-compaction): 在缩减 Agent 长历史前使用类型化问题。
- [Jev vs GPT and Claude: choosing a decision layer](https://jevmodel.app/guides/jev-vs-llm): Compare Jev typed probabilities with GPT and Claude structured outputs. Choose routing, generation or a hybrid workflow using your own test cases.
- [Jev vs GPT 与 Claude：如何选择判断层](https://jevmodel.app/zh/guides/jev-vs-llm): 对比 Jev 类型化概率与 GPT、Claude 的结构化输出；通过真实测试案例选择路由判断、内容生成或混合工作流。
- [Jev or rules?](https://jevmodel.app/guides/jev-vs-rules): Decide when a model helps and when ordinary code is enough.
- [Jev 与规则引擎怎么选？](https://jevmodel.app/zh/guides/jev-vs-rules): 分清模型何时有用、普通代码何时足够。
- [Evaluate a Jev workflow](https://jevmodel.app/guides/evaluation): Test labels, uncertainty, and real outcomes before automation.
- [评估 Jev 工作流](https://jevmodel.app/zh/guides/evaluation): 在自动化前测试标签、不确定性和真实结果。
- [Private runs and history](https://jevmodel.app/guides/privacy-and-history): What the JevModel workbench stores and how to remove it.
- [运行记录与隐私](https://jevmodel.app/zh/guides/privacy-and-history): 了解 JevModel 工作台保存什么，以及如何删除。
- [Ways to access Jev](https://jevmodel.app/guides/access-paths): Choose a provider path and keep credentials on your server.
- [Jev 的接入方式](https://jevmodel.app/zh/guides/access-paths): 选择模型提供方，并将凭据留在服务端。
- [Is Jev open source?](https://jevmodel.app/guides/is-jev-open-source): Jev is a hosted model: TypeSafe AI does not publish Jev weights. See which Jev GitHub repos exist, what is official, and which open-source Jev alternatives you can self-host.
- [Jev 是开源的吗？](https://jevmodel.app/zh/guides/is-jev-open-source): Jev 是托管模型，TypeSafe AI 没有公开 Jev 权重。本文梳理与 Jev 相关的 GitHub 仓库、哪些是官方的，以及可以自托管的开源 Jev 替代方案。
- [What is Laya?](https://jevmodel.app/guides/what-is-laya): An open decision model with a Jev-shaped task, from a different team.
- [Laya 是什么？](https://jevmodel.app/zh/guides/what-is-laya): 了解由另一团队开发、同样处理类型化判断的开放模型。
- [Jev vs Laya](https://jevmodel.app/guides/jev-vs-laya): Hosted Jev access and open local deployment solve different constraints.
- [Jev 与 Laya 怎么选？](https://jevmodel.app/zh/guides/jev-vs-laya): 比较 Jev 的托管接入与 Laya 的本地部署边界。
- [Jev vs OpenJev](https://jevmodel.app/guides/jev-vs-openjev): API familiarity is useful, but runtime and model behavior still differ.
- [Jev 与 OpenJev 怎么选？](https://jevmodel.app/zh/guides/jev-vs-openjev): 接口相似有助接入，但运行方式与模型行为仍然不同。
- [Jev vs djev](https://jevmodel.app/guides/jev-vs-djev): Compare text decisions with a DiffusionGemma-based multimodal approach.
- [Jev 与 djev 怎么选？](https://jevmodel.app/zh/guides/jev-vs-djev): 比较文本判断与基于 DiffusionGemma 的多模态方案。
- [SemIf vs Jev: Benchmarks, Calibration, and Deployment](https://jevmodel.app/guides/jev-vs-semif): Compare SemIf vs Jev using primary sources: option scoring, benchmark limits, CPU and GPU deployment, calibration, and a practical workflow evaluation plan.
- [SemIf vs Jev：评测、概率校准与部署选型](https://jevmodel.app/zh/guides/jev-vs-semif): 依据官方文档与原始仓库比较 SemIf vs Jev：解释公开评测的边界、CPU/GPU 与 Apple Silicon 部署、概率校准、数据路径和总成本，并给出客服分流示例与选型检查方法。
- [Jev vs Jev-Omni: text and multimodal decisions](https://jevmodel.app/guides/jev-omni): Jev-Omni is an independent 12B model for text, image, audio, and video decisions. Compare its inputs and hardware needs with hosted Jev.
- [Jev 与 Jev-Omni：文本与多模态判断](https://jevmodel.app/zh/guides/jev-omni): Jev-Omni 是独立的 12B 文本、图像、音频和视频判断模型；了解它与托管 Jev 的输入及硬件区别。
- [JevModel pricing and free Jev runs](https://jevmodel.app/guides/pricing-and-free-tier): Understand the 100,000 signup tokens, Flow usage, input-token billing, packs and rollover plans. Choose a plan after measuring your own workload.
- [JevModel 价格与 Jev 免费额度](https://jevmodel.app/zh/guides/pricing-and-free-tier): 了解注册赠送的 10 万 Token、Flow 用量、输入 Token 计费、Token 包与可结转套餐；先测实际工作量，再选择方案。
- [AI Decision Flows with Jev and human review](https://jevmodel.app/guides/decision-flows): Build a Jev decision flow for support routing, add an uncertain-answer branch and call the saved graph through the API. Learn limits and billing.
- [Jev AI 决策流与人工复核分支](https://jevmodel.app/zh/guides/decision-flows): 搭建 Jev 客服决策流、添加不确定结果人工复核分支，并通过 API 调用已保存流程；了解路径、限制与计费。
- [Batch text classification with the JevModel API](https://jevmodel.app/guides/batch-text-classification-api): Classify CSV or JSONL rows with Jev Choice questions. Reuse the normal API, preserve row IDs and export results without inventing a batch endpoint.
- [Jev API 批量文本分类：CSV 与 JSONL](https://jevmodel.app/zh/guides/batch-text-classification-api): 用 Jev Choice 分类 CSV 或 JSONL 行，复用普通 API、保留行 ID 并导出结果；了解大小限制、失败处理与计费。