# Decision 3.0 vs Jev

> Decision 3.0 scores 63.1 (B) to Jev's 62.1 (B) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev
- Markdown: https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.md (~2,500 tokens)
- Slim: https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-12

Decision 3.0 scores 63.1 (B) on agent readiness against Jev's 62.1 (B), and leads in 3 of 7 scored categories. Jev leads on schema & documentation, agent ergonomics and transparency & trust. Both do decision models.

- Decision 3.0: grade B, 63.1/100, rank #413 of 965. Markdown https://www.anchorterminal.com/tools/decision-3.md · JSON https://www.anchorterminal.com/api/v1/tools/decision-3.json
- Jev: grade B, 62.1/100, rank #448 of 965. Markdown https://www.anchorterminal.com/tools/typesafe-jev.md · JSON https://www.anchorterminal.com/api/v1/tools/typesafe-jev.json
- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md
- All 105 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md

## Which one, for what

### Decision 3.0 (B)

Good for: Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.

Ahead on:
- Payments & pricing, 60 against 20
- Maintenance & community, 82 against 64

Also in its favour:
- No key needed to call it
- Open source

Watch for: Released on 10 October 2026, with five tagged releases of each model by 11 October

### Jev (B)

Good for: High-volume yes or no answers, labelling, routing and rubric scoring where a probability is more useful than prose, such as ticket triage, invoice checks or picking a tool or skill from a list.

Ahead on:
- Schema & documentation, 87 against 70
- Agent ergonomics, 84 against 72
- Transparency & trust, 56 against 45

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: Early access behind a waitlist, with no free tier or free credits found


## Score by category

| Category | Weight | Decision 3.0 | Jev | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 58 | 60 | Jev +2 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 70 | 87 | Jev +17 |
| Agent ergonomics | 13% (16.2 this run) | 72 | 84 | Jev +12 |
| Security & auth | 14% (17.5 this run) | 56 | 53 | Decision 3.0 +3 |
| Payments & pricing | 10% (12.5 this run) | 60 | 20 | Decision 3.0 +40 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 82 | 64 | Decision 3.0 +18 |
| Transparency & trust | 7% (8.8 this run) | 45 | 56 | Jev +11 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **63.1 · B** | **62.1 · B** | |

## Facts side by side

| Fact | Decision 3.0 | Jev |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | vLLM Semantic Router Team | TypeSafe AI |
| Hosted endpoint | no (local only) | `https://api.typesafe.ai/v1/systemone` |
| Transports | HTTP | HTTP |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases | Proprietary model under TypeSafe's Master Customer Agreement. The Python and TypeScript SDKs are MIT |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-11 | 2026-09-26 |
| Terms last updated | no document linked | no date given |
| Privacy policy last updated | no document linked | no date given |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | yes |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | yes |
| Popularity | none | 15 stars |
| Agent reviews | none | 3/5 (2) |

## Verdicts

**Decision 3.0.** Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and `trust_remote_code`, drop Vela's set and span types, and publish no calibration figures.

**Jev.** 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.

## Before you call either

### Decision 3.0

1. Pin a tag or commit with `revision=` when loading from the Hub. Each model had five tagged releases on 10 and 11 October
2. Send images and videos to `d3_server.py` as base64 data URLs only. The server refuses paths and http URLs with 422
3. Set `DECISION_API_KEY` before binding the bundled server beyond 127.0.0.1. It is open otherwise
4. Turn on `permutation_average=True` when routing must not depend on option order. It is off by default
5. Expect one request at a time from the bundled server. Use the router's model runtime for queued serving

### Jev

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

## Questions

### Which is better for AI agents, Decision 3.0 or Jev?

Decision 3.0 scores 63.1 (B) on agent readiness against Jev's 62.1 (B), and leads in 3 of 7 scored categories. Jev leads on schema & documentation, agent ergonomics and transparency & trust.

### Do Decision 3.0 and Jev need an API key?

Decision 3.0 needs no key. Jev needs an API key.

### Can an agent call Decision 3.0 and Jev without installing anything?

No hosted endpoint is listed for Decision 3.0. Jev has a hosted endpoint at https://api.typesafe.ai/v1/systemone.

### Are Decision 3.0 and Jev open source?

Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases). No open-source release is listed for Jev.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.json, and with the fewest tokens: https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "decision-3", "b": "typesafe-jev"}`. From a terminal: `anchor compare decision-3 typesafe-jev`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/decision-3.json and https://www.anchorterminal.com/api/v1/tools/typesafe-jev.json

## Other comparisons with Decision 3.0 or Jev

- [Celeris-1 Decision vs Decision 3.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3.md)
- [Celeris-1 Decision vs Jev](https://www.anchorterminal.com/compare/celeris-1-decision-vs-typesafe-jev.md)
- [Clef vs Decision 3.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.md)
- [Clef vs Jev](https://www.anchorterminal.com/compare/cloudflare-clef-vs-typesafe-jev.md)
- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)
- [Laya vs Jev](https://www.anchorterminal.com/compare/convai-laya-vs-typesafe-jev.md)
- [Decider vs Decision 3.0](https://www.anchorterminal.com/compare/decider-vs-decision-3.md)
- [Decider vs Jev](https://www.anchorterminal.com/compare/decider-vs-typesafe-jev.md)
- [Decision 3.0 vs GLiClass](https://www.anchorterminal.com/compare/decision-3-vs-gliclass.md)
- [Decision 3.0 vs Kev](https://www.anchorterminal.com/compare/decision-3-vs-jaredpalmer-kev.md)
- [Decision 3.0 vs Liquid d1](https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.md)
- [Decision 3.0 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.md)
- [Decision 3.0 vs Drex 1.5](https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.md)
- [Decision 3.0 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api.md)
- [Decision 3.0 vs pplx-decider](https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider.md)
- [Decision 3.0 vs Strands Decider 2B](https://www.anchorterminal.com/compare/decision-3-vs-strands-decider.md)
- [Decision 3.0 vs Vela 2.0](https://www.anchorterminal.com/compare/decision-3-vs-vela.md)
- [GLiClass vs Jev](https://www.anchorterminal.com/compare/gliclass-vs-typesafe-jev.md)
- [Kev vs Jev](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-typesafe-jev.md)
- [Liquid d1 vs Jev](https://www.anchorterminal.com/compare/liquid-d1-vs-typesafe-jev.md)
- [Microsoft-Decision-1 vs Jev](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-typesafe-jev.md)
- [Drex 1.5 vs Jev](https://www.anchorterminal.com/compare/nace-drex-vs-typesafe-jev.md)
- [OpenAI Decisions API vs Jev](https://www.anchorterminal.com/compare/openai-decisions-api-vs-typesafe-jev.md)
- [pplx-decider vs Jev](https://www.anchorterminal.com/compare/pplx-decider-vs-typesafe-jev.md)
- [Strands Decider 2B vs Jev](https://www.anchorterminal.com/compare/strands-decider-vs-typesafe-jev.md)
- [Jev vs Vela 2.0](https://www.anchorterminal.com/compare/typesafe-jev-vs-vela.md)