Search
Search Jev resources
V1 search matches title, description, tags and category. 30 results.
Jev TypeScript TutorialTutorialsUse @typesafe-ai/sdk to call Jev from TypeScript or JavaScript with inferred Choice, Score, and Noul answers.Jev Python TutorialTutorialsInstall typesafe-sdk and call TypeSafe Jev from Python with Choice, Score, and Noul questions.Jev cURL ExamplesTutorialsCall the TypeSafe Jev HTTP API with cURL: authentication, mixed questions, listing models, and error codes.What is TypeSafe AI?LearnTypeSafe AI is the company behind Jev, a System One model for typed decisions. Jev is the model; TypeSafe is the vendor.What is Jev AI?LearnWhat is Jev? Jev is TypeSafe's Jev AI model — a System One model for classification, routing and scoring, not a chat LLM.Jev PricingDevelopersJev API pricing from TypeSafe's official models page: $0.042 per million input tokens, output free, last verified 2026-09-20.Jev on OpenRouter and VercelDevelopersCall TypeSafe Jev through OpenRouter or Vercel AI Gateway when you do not have a TypeSafe key yet, or already bill through those platforms.Jev LimitationsLearnWhat Jev cannot do well: generation, math, dates, counting, large noisy state, and other jev-1.13 jagged edges from official docs.Is Jev an LLM?LearnJev is TypeSafe's System One model, not a chat LLM. It understands natural-language state but returns typed Choice, Score, and Noul answers instead of generated text.How to Use JevLearnHow to use TypeSafe Jev: get access, send state plus Choice, Score, or Noul questions, and branch on typed answers in Python, TypeScript, or cURL.How Jev WorksLearnHow TypeSafe Jev works: architecture, parallel sampler, and how one state is evaluated against typed questions.Jev GitHub and Open SourceDevelopersThere is no official public Jev model repo. Official clients are typesafe-sdk and @typesafe-ai/sdk. Community GitHub tools still call the hosted API.Getting Started with JevLearnHow to use Jev: get waitlist or console access, set TYPESAFE_API_KEY, and make your first TypeSafe Jev API call with Playground, cURL, Python, or TypeScript.Jev FAQLearnIndependent answers to common Jev AI questions: what it is, how the API works, pricing, primitives, and limits.Jev APIDevelopersTypeSafe Jev API documentation: authentication, POST /v1/systemone, question types, responses, errors and examples.Jev System One ModelConceptsWhat is a System One model? Jev is TypeSafe's first System One model: fast structured decisions for software, trained with RLCD.Jev ScoreConceptsScore is Jev's ordered rubric primitive. It returns a probability-weighted value, a legend, and confidence.Jev RLCDConceptsRLCD is TypeSafe's name for Reinforcement Learning for Calibrated Decisions, the training method behind Jev's System One probabilities.Jev NoulConceptsNoul is Jev's yes/no primitive. It returns the probability that a statement is true. There is no separate confidence field.Jev ChoiceConceptsChoice is Jev's question type for picking one option from a closed set, with probabilities and confidence.Route Customer Support Tickets with JevRoutingUse Jev Choice, Noul, and Score together to route support tickets, flag urgency, and keep assignment logic in code.Detect Customer Intent with JevClassificationA Jev Choice example for intent detection: closed intents, an other escape hatch, and code that owns the handler map.Score Inbound Leads with JevScoringA Jev Score example for lead quality. Levels describe situations, not adjectives. Do not turn the fractional score into a fake dollar value.Score Customer Sentiment with JevScoringJev sentiment as a Score: situational levels, a full probability distribution, and a code path that escalates angry mail.Moderate User Content with JevModerationIndependent Jev moderation example based on TypeSafe's LLM guardrails pattern: atomic hazard questions, a severity Score, thresholds in code.Filter RAG Passages with JevRAGJev RAG filtering example: one request per passage for relevance, contradiction, and injection — then code decides what reaches the answer model.Route Requests to the Right AI Model with JevRoutingJev as a model router: Choice over snap_judgment, write_text, and deep_reason, then your gateway picks the backend.Classify Documents with JevClassificationDocument-type classification with Jev Choice. Different from customer intent: this page asks what the file is, not what the person wants.Detect Escalations with JevSupportEscalation as a Jev Noul: one yes/no probability, optional criteria, no separate confidence field.Select an Agent Tool with JevAgentsJev tool-selection example inspired by TypeSafe's skill-suggestion cookbook: a Choice over tool names plus a Noul for 'should we call anything?'.