Citation Check Against the Source Text
Generate an analysis to verify if a cited section supports or contradicts a factual claim, returning structured outputs.

Jev is TypeSafe AI's decision model. It does not write text: you send it a block of state and a set of typed questions, and it returns probabilities in under half a second. Three primitives cover everything: Choice picks one option from a list, Score places the state on a rubric, Noul answers yes or no with a probability. It is built to sit inside code as a fast, cheap judgment call before or after the expensive LLM.
Intent routing and triage in front of an LLM, input and output guardrails, reranking retrieval shortlists, RAG passage filtering, composite scoring of resumes or leads, moderation decisions, and any high-volume classification where a text model is too slow or too expensive.
POST to https://api.typesafe.ai/v1/systemone with a bearer key, a model of jev-latest, a state that is a string, object or array, and a questions map. Each question is a Choice (up to 255 options), a Score (2 to 10 ordered levels) or a Noul (yes/no). Read the answers map in code and apply your own thresholds. Python and JavaScript SDKs and an agent skill for Claude Code and Codex are available.
Returns typed answers with a probability distribution and a confidence figure, never prose. Evaluates every question in a request in parallel, so ten questions cost about the same time as one. Reads dates and numbers as text, cannot count, and answers the question you wrote rather than the one you meant.
Ask one thing per question and put every question in a single request. Give Choice options a what, a not_for and examples when they could be confused. Describe Score levels as situations, not degrees. Keep arithmetic, counting and date logic in your code, and route on confidence: act above 0.9, confirm between 0.5 and 0.9, hand off below 0.5.
Early access via waitlist. $0.042 per million input tokens, output is free. Multiple questions in one request share the same input cost.
Generate an analysis to verify if a cited section supports or contradicts a factual claim, returning structured outputs.
Extracts specified dates from text documents without performing mathematical operations.
Generate a judgment on whether a candidate passage provides specific information needed by a query excerpt, producing a JSON output.
Generate safety evaluations for assistant replies using predefined scoring dimensions and routing logic.
Generate a JSON-based scorecard for evaluating resumes across four dimensions in alignment with job descriptions.
Generate JSON-based classifications for routing customer support tickets, focusing on department, frustration level, and refund requests.

Claude is Anthropic's family of AI assistants, built for serious reasoning, long documents, and agentic coding. Its strength is agentic coding and honest analysis, and it holds huge context so you can hand it whole files instead of snippets.
LLM
ChatGPT is the general-purpose AI assistant most people reach for first. It writes, reasons, codes, and answers across almost any topic, which makes it the default tool for everyday work. Its real ceiling shows once you prompt it with structure instead of one-line questions.
LLM
Gemini is Google's flagship multimodal AI, built into the Gemini app, Google Workspace, and Google Cloud. It plugs straight into Gmail, Docs, Search, and Android, and handles text, images, audio, video, and long documents natively.
LLM
Grok is xAI's conversational AI, available at grok.com and built into X, with live access to X's real-time data. That live data makes it strong on current events, and its style is more candid with fewer refusals than most rivals.
LLM
DeepSeek is a Chinese AI lab that releases open-weight models alongside a free chat app and one of the cheapest developer APIs available. It competes with frontier models on coding and reasoning while costing a fraction to run at scale, and the weights are open so you can self-host.
LLM
European open-weight LLM family — fast, multilingual, enterprise-friendly.
LLM