Evaluate text at scale with Jev.
Jev is a structured judgment model by TypeSafe. It outputs exact booleans, choices, and scores. You can process up to 32 independent questions in parallel per request.
Call Jev directly from your workspace.
The Kollab Agent invokes Jev automatically when you ask for structured evaluations. You can also run it manually via the CLI for scripts and pipelines.
npm install -g @kollab/cli
kollab login
echo '{
"state": "Help! My payouts have been failing for 3 days.",
"questions": {
"is_urgent": { "type": "noul", "instructions": "Does this convey urgency?" },
"department": { "type": "choice", "instructions": "Which team should handle this?",
"criteria": { "billing": "Payments, invoicing, refunds", "technical": "Bugs, outages, integrations", "sales": "Pricing, upgrades, new accounts" } }
}
}' | kollab tool run jev --jsonPart of the Kollab model armory.
Access Jev alongside a complete suite of models for text, vision, video, and audio tasks.
Structured judgment use cases.
Run specific evaluation tasks with Jev.
Performance benchmarks.
Fast execution and high consistency for batch classification tasks.
13 questions in one call: 0.27s vs 2.71s for 13 separate calls
TypeSafe cookbookCLERC legal dataset, 40 queries, BM25 top-30 shortlist
TypeSafe cookbook6,003 ratings checked · $160 vs $33,000 per million judgments
Good Start Labs0.35s median vs 8.83s · detected 6/7 seeded defects
Every.to5,733-email test set, close to a tuned TF-IDF baseline's 98.87%
bitnovus (independent)Real-world applications.
How developers and researchers are using Jev in production.
Spam and Auto-Reply Detection
Freek Van der Herten processes incoming helpdesk tickets with 3 parallel questions in 639ms. This achieves 48 requests per second at a monthly cost of $0.36.
Financial Research Consistency
Good Start Labs uses Jev to verify large sets of financial reports efficiently and consistently.
Writing Vibe Checks
Every.to evaluates drafted articles with Jev. The model flags seeded writing defects with a median speed of 0.35 seconds.
LLM Observability Scoring
Langfuse integrated Jev into their evaluation system to automate prompt scoring and feedback data.
Cloudflare Workers AI Integration
Cloudflare added the Jev model to their Workers AI platform for global edge inference.
Seed Funding Announcement
TypeSafe AI raised $40M to build specialized models for software applications.
Structured State Management
Jev powers an official demo playing Doom through structured game state outputs.
Frequently asked questions.
What is Jev and how does it differ from standard chat models?+
Jev is a structured judgment model. It outputs exact booleans, choices, and scores. It skips conversational text entirely and returns pure data.
How do I use Jev in Kollab?+
The Kollab Agent invokes Jev automatically when you describe a task requiring structured judgment. You can also call it directly from your terminal using the `kollab tool run jev` command.
How is the pricing calculated?+
Input tokens cost $0.042 per million. Output tokens are completely free.
Does Jev support Chinese, Japanese, and Korean?+
Yes. The accuracy for CJK languages is currently lower than English.
Are the confidence probabilities absolutely accurate?+
Independent audits show Jev's output probabilities are not strictly calibrated. Treat them as relative, monotonic scores. We recommend spot-checking high-risk tasks.
Can Jev process images or audio?+
Jev only processes plain text up to 80,000 characters. You must transcribe audio or extract text from images first. Kollab provides other models like GPT Image 2 and Grok STT for direct media processing.
Start evaluating text with Jev.
Run high-volume classification and scoring tasks directly in your workspace.