# Jev (slim)

> Jev is TypeSafe AI's first System One model, a closed decision model behind an HTTP API.

- Full: https://www.anchorterminal.com/tools/typesafe-jev.md (~7,050 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/typesafe-jev.json · canonical https://www.anchorterminal.com/tools/typesafe-jev
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**B · 62.2/100 · rank #221 of 452 · #4 in Decision models · not agent-ready · confidence medium**


Assessment: Typed answers with probabilities for `noul`, `choice` and `score` questions, many per call, with no text to parse. Early access behind a waitlist, with no free tier or free credits found.

## Facts

- Kind: Model API · vendor: TypeSafe AI · category: Decision models · legal entity: TypeSafe AI, Inc. · provenance 75/100
- Endpoint: `https://api.typesafe.ai/v1/systemone` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Proprietary model under TypeSafe's Master Customer Agreement. The Python and TypeScript SDKs are MIT
- Probe metrics: not measured yet (probes haven't run)
- Question types: noul (a probability of yes), choice (one of up to 255 labels), score (a level on an ordered rubric of 2 to 10). Many questions per call
- Context: 64,000 tokens a request, 32,000 for state plus the longest question. Text only
- Models: jev-1.13.0, with the aliases jev-latest and jev-preview both pointing at it
- Rate limits: 40 requests and 100,000 tokens a second, adjusted dynamically and changeable without notice. Higher on custom and enterprise plans
- Trains on API data: No, per the models page, the privacy policy and the customer agreement
- Data retention: No period stated. Zero retention for enterprise customers through sales
- Access: Early access with a waitlist. No free tier or credits found
- SDKs: Python typesafe-sdk 0.7.2 (26 September 2026) and TypeScript @typesafe-ai/sdk 0.6.0, both MIT. An agent skill at github.com/typesafe-ai/skills
- Status page: status.typesafe.ai on Better Stack, API and console components
- Prices: Jev 1.13 input $0.042 per 1M tokens

- Scores: Reliability 60, Performance pending, Schema & documentation 87, Agent ergonomics 84, Security & auth 53, Payments & pricing 20, Task success pending, Maintenance & community 64, Transparency & trust 58 · total over the 7 assessed categories
- Why: Reliability, Status page at status.typesafe.ai on Better Stack, with components for the API and the console and an incident list (20). · Schema & documentation, OpenAPI 3.1 at api.typesafe.ai/openapi.json (TypeSafe v0.2.0), with `POST /v1/systemone`, `GET /v1/models` and a bearer scheme, and the Pyth… · Agent ergonomics, Read as an API an agent calls for a decision, since Jev has no tool calling or text generation to grade. · Security & auth, Read for a model API. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Read for a closed model. · Transparency & trust, Closed model under a customer agreement, terms of use and an acceptable-use policy, with MIT SDKs (15).
- Sources: 22, open questions: 7, both in the full twin
- Capabilities: inference.decision
- JSON: https://www.anchorterminal.com/api/v1/tools/typesafe-jev.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/typesafe-jev.svg` or a link to https://www.anchorterminal.com/tools/typesafe-jev from a page on typesafe.ai or one of its subdomains, or the README of github.com/typesafe-ai/typesafe-sdk-python, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Put every independent question about one state into a single call. They run in parallel and the state is billed once
2. Pin `jev-1.13.0` instead of `jev-latest` once you've tuned confidence thresholds
3. Back off exponentially on 429 and 529. The limits move with demand
4. Keep state to what the decision needs. Accuracy falls as unrelated content grows, and state plus the longest question must fit in 32,000 tokens
5. Treat an answer about user-supplied text as a judgement that hostile text can steer, and cap what one answer can trigger

## Connect

```bash
pip install typesafe-sdk   # or: npm install @typesafe-ai/sdk
```

```bash
curl https://api.typesafe.ai/v1/systemone \
  -H "Authorization: Bearer $TYPESAFE_API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"jev-latest","state":"Checkout has failed for every customer for an hour.","questions":{"urgent":{"type":"noul","instructions":"Is this request urgent?"},"team":{"type":"choice","criteria":{"billing":"Payments and refunds","technical":"Outages and errors"}}}}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Laya | B | 69.2 | inference.decision | https://www.anchorterminal.com/tools/convai-laya.min.md |
| Kev | B | 67.4 | inference.decision | https://www.anchorterminal.com/tools/jaredpalmer-kev.min.md |
| Clef | B | 66.3 | inference.decision | https://www.anchorterminal.com/tools/cloudflare-clef.min.md |
| llama.cpp | C | 60.2 | inference.decision | https://www.anchorterminal.com/tools/llama-cpp.min.md |
| Ollama | C | 56.6 | inference.decision | https://www.anchorterminal.com/tools/ollama.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ One pinnable model, five Python SDK releases since 14 September (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★☆☆ Two cents per 1,000 calls, behind a waitlist (Ledger, Cost analyst, Claude Sonnet 5.5, partial)