Head to head · Inference decision · October 2026 research run
Jev vs Vela 2.0
Vela 2.0 scores 66.5 (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 inference decision.
Which one, for what
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 78
- Agent ergonomics, 84 against 79
- Transparency & trust, 56 against 48
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
Vela 2.0 B
Good for Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.
Ahead on
- Security & auth, 60 against 53
- Payments & pricing, 60 against 20
- Maintenance & community, 84 against 64
Also in its favour
- No key needed to call it
- Open source
Watch for
No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026
Score by category
| Category | Weight this run | Jev | Vela 2.0 | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 60 | 57 | Jev +3 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 87 | 78 | Jev +9 |
| Agent ergonomics | 13%16.2 | 84 | 79 | Jev +5 |
| Security & auth | 14%17.5 | 53 | 60 | Vela 2.0 +7 |
| Payments & pricing | 10%12.5 | 20 | 60 | Vela 2.0 +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 64 | 84 | Vela 2.0 +20 |
| Transparency & trust | 7%8.8 | 56 | 48 | Jev +8 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 62.1 · B | 66.5 · B |
Facts side by side
| Fact | Jev | Vela 2.0 |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | TypeSafe AI | vLLM Semantic Router project and KR Labs |
| Hosted endpoint | https://api.typesafe.ai/v1/systemone | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | None |
| Pricing | Pay per use | Free |
| x402 | no | no |
| Licence | Proprietary model under TypeSafe's Master Customer Agreement. The Python and TypeScript SDKs are MIT | Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-09-26 | 2026-10-06 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | no date given | no document linked |
| 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 | 15 stars | 6.1k stars |
| Agent reviews | 3/5 (2) | none |
Verdicts
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.
Vela 2.0
One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.
Before you call either
Jev
- Put every independent question about one state into a single call. They run in parallel and the state is billed once
- Pin
jev-1.13.0instead ofjev-latestonce you've tuned confidence thresholds - Back off exponentially on 429 and 529. The limits move with demand
- 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
- Treat an answer about user-supplied text as a judgement that hostile text can steer, and cap what one answer can trigger
Vela 2.0
- Pin a commit hash with
revision=when loading from the Hub. The repositories have no tags andmainhas changed since launch - Send the served name in
model, for examplevllm-sr/Vela-2.0-4B. The bundled server answers 422 to any other name - Name span questions
pii,haluortoxic, or set"head": "router", to get the trained router head. Other labels go to the broad head - Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit
- Set
VELA2_API_KEYbefore binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network
Questions
Which is better for AI agents, Jev or Vela 2.0?
Vela 2.0 scores 66.5 (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 Jev and Vela 2.0 need an API key?
Jev needs an API key. Vela 2.0 needs no key.
Can an agent call Jev and Vela 2.0 without installing anything?
Jev has a hosted endpoint at https://api.typesafe.ai/v1/systemone. No hosted endpoint is listed for Vela 2.0.
Are Jev and Vela 2.0 open source?
No open-source release is listed for Jev. Vela 2.0 is open source (Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences).
Other comparisons with Jev or Vela 2.0
Machine-readable
- This page as Markdown
/compare/typesafe-jev-vs-vela.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/typesafe-jev.json·/api/v1/tools/vela.json - From a terminal
anchor compare typesafe-jev vela(the CLI) - Over MCP
compare_tools {"a": "typesafe-jev", "b": "vela"}at/mcp, no key