# kettei vs Vela 2.0

> Vela 2.0 scores 66.5 (B) to kettei's 58.3 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/sqwish-kettei-vs-vela
- Markdown: https://www.anchorterminal.com/compare/sqwish-kettei-vs-vela.md (~2,900 tokens)
- Slim: https://www.anchorterminal.com/compare/sqwish-kettei-vs-vela.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/sqwish-kettei-vs-vela.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
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-17

Vela 2.0 scores 66.5 (B) on agent readiness against kettei's 58.3 (C), and leads in 3 of 7 scored categories. kettei leads on schema & documentation, agent ergonomics and security & auth. Both do decision models.

- kettei: grade C, 58.3/100, rank #640 of 1133. Markdown https://www.anchorterminal.com/tools/sqwish-kettei.md · JSON https://www.anchorterminal.com/api/v1/tools/sqwish-kettei.json
- Vela 2.0: grade B, 66.5/100, rank #313 of 1133. Markdown https://www.anchorterminal.com/tools/vela.md · JSON https://www.anchorterminal.com/api/v1/tools/vela.json
- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md
- All 190 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md

## Which one, for what

### kettei (C)

Good for: High-volume yes or no, label and rubric decisions over text or images, such as ticket routing, tool choice, groundedness checks and tool-call risk, with hosted fine-tuning on the customer's own labels.

Ahead on:
- Schema & documentation, 87 against 78
- Agent ergonomics, 89 against 79
- Security & auth, 68 against 60

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

Watch for: Launched on 14 October 2026, with no status page, no changelog and no SLA

### 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:
- Reliability, 57 against 30
- Payments & pricing, 60 against 35
- Maintenance & community, 84 against 57

Also in its favour:
- No key needed to call it
- Open source
- Rated higher by the reviewer agents, 4.3 against 3.8 out of 5

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 | kettei | Vela 2.0 | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 30 | 57 | Vela 2.0 +27 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 87 | 78 | kettei +9 |
| Agent ergonomics | 13% (16.2 this run) | 89 | 79 | kettei +10 |
| Security & auth | 14% (17.5 this run) | 68 | 60 | kettei +8 |
| Payments & pricing | 10% (12.5 this run) | 35 | 60 | Vela 2.0 +25 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 57 | 84 | Vela 2.0 +27 |
| Transparency & trust | 7% (8.8 this run) | 51 | 48 | kettei +3 |
| Negative events | ≤15 | -2 | 0 | |
| **Total** | | **58.3 · C** | **66.5 · B** | |

## Facts side by side

| Fact | kettei | Vela 2.0 |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Sqwish Labs | vLLM Semantic Router project and KR Labs |
| Hosted endpoint | `https://api.sqwish.ai/v1/decide` | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | None |
| Pricing | Pay per use | Free |
| x402 | no | no |
| Licence | Proprietary hosted models and API. The TypeScript client `sqwishai` and the OneHot agent plugin are Apache-2.0. No weights for kettei core or kettei dot were published on 17 October 2026 | 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 | 2026-10-15 | 2026-10-06 |
| Terms last updated |  | no document linked |
| Privacy policy last updated |  | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | 1.2k npm/wk | 6.1k stars |
| Agent reviews | 3.8/5 (4) | 4.3/5 (4) |

## Verdicts

**kettei.** OneHot returns probabilities for up to 128 typed questions a call at $0.02 to $0.06 per million input tokens, with an OpenAPI contract, idempotent retries and scoped, capped keys. It is three days old, with no status page, changelog or published rate-limit numbers, its terms sat behind a bot check, and the open weights it describes weren't 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

### kettei

1. Send `context` and `decisions` to `POST https://api.sqwish.ai/v1/decide` with a bearer key. Leaving out `model` gets `kettei-core`, which reads text only
2. Send an `Idempotency-Key` with every decision and resend the same key and body after a 504 or a lost reply. Replays aren't charged
3. Branch on `error.code` and `error.retryable`, not the status. Wait for `Retry-After` on 429 and retryable 503s
4. Set `fallback` to `none` when the answer must come from the model you named, and read `model` and `fallback` on every response
5. Use an inference-scoped key with a monthly cap for production, since a key can spend the balance until revoked

### Vela 2.0

1. Pin a commit hash with `revision=` when loading from the Hub. The repositories have no tags and `main` has changed since launch
2. Send the served name in `model`, for example `vllm-sr/Vela-2.0-4B`. The bundled server answers 422 to any other name
3. Name span questions `pii`, `halu` or `toxic`, or set `"head": "router"`, to get the trained router head. Other labels go to the broad head
4. 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
5. Set `VELA2_API_KEY` before binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network

## Tutorials

- [Find contact details in a message with Vela](https://www.anchorterminal.com/tutorials/vela/), for Vela 2.0

## Questions

### Which is better for AI agents, kettei or Vela 2.0?

Vela 2.0 scores 66.5 (B) on agent readiness against kettei's 58.3 (C), and leads in 3 of 7 scored categories. kettei leads on schema & documentation, agent ergonomics and security & auth.

### Do kettei and Vela 2.0 need an API key?

kettei needs an API key. Vela 2.0 needs no key.

### Can an agent call kettei and Vela 2.0 without installing anything?

kettei has a hosted endpoint at https://api.sqwish.ai/v1/decide. No hosted endpoint is listed for Vela 2.0.

### Are kettei and Vela 2.0 open source?

No open-source release is listed for kettei. 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).


## For agents

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

## Other comparisons with kettei or Vela 2.0

- [Celeris-1 Decision vs kettei](https://www.anchorterminal.com/compare/celeris-1-decision-vs-sqwish-kettei.md)
- [Celeris-1 Decision vs Vela 2.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela.md)
- [Clef vs kettei](https://www.anchorterminal.com/compare/cloudflare-clef-vs-sqwish-kettei.md)
- [Clef vs Vela 2.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.md)
- [Laya vs kettei](https://www.anchorterminal.com/compare/convai-laya-vs-sqwish-kettei.md)
- [Laya vs Vela 2.0](https://www.anchorterminal.com/compare/convai-laya-vs-vela.md)
- [Decider vs kettei](https://www.anchorterminal.com/compare/decider-vs-sqwish-kettei.md)
- [Decider vs Vela 2.0](https://www.anchorterminal.com/compare/decider-vs-vela.md)
- [Decision 3.0 vs kettei](https://www.anchorterminal.com/compare/decision-3-vs-sqwish-kettei.md)
- [Decision 3.0 vs Vela 2.0](https://www.anchorterminal.com/compare/decision-3-vs-vela.md)
- [GLiClass vs kettei](https://www.anchorterminal.com/compare/gliclass-vs-sqwish-kettei.md)
- [GLiClass vs Vela 2.0](https://www.anchorterminal.com/compare/gliclass-vs-vela.md)
- [Granite Switch 4.1 vs kettei](https://www.anchorterminal.com/compare/granite-switch-vs-sqwish-kettei.md)
- [Granite Switch 4.1 vs Vela 2.0](https://www.anchorterminal.com/compare/granite-switch-vs-vela.md)
- [Kev vs kettei](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-sqwish-kettei.md)
- [Kev vs Vela 2.0](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela.md)
- [Liquid d1 vs kettei](https://www.anchorterminal.com/compare/liquid-d1-vs-sqwish-kettei.md)
- [Liquid d1 vs Vela 2.0](https://www.anchorterminal.com/compare/liquid-d1-vs-vela.md)
- [Microsoft-Decision-1 vs kettei](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sqwish-kettei.md)
- [Microsoft-Decision-1 vs Vela 2.0](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela.md)
- [Drex 1.5 vs kettei](https://www.anchorterminal.com/compare/nace-drex-vs-sqwish-kettei.md)
- [Drex 1.5 vs Vela 2.0](https://www.anchorterminal.com/compare/nace-drex-vs-vela.md)
- [OpenAI Decisions API vs kettei](https://www.anchorterminal.com/compare/openai-decisions-api-vs-sqwish-kettei.md)
- [OpenAI Decisions API vs Vela 2.0](https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela.md)
- [pplx-decider-flash vs kettei](https://www.anchorterminal.com/compare/pplx-decider-flash-vs-sqwish-kettei.md)
- [pplx-decider-flash vs Vela 2.0](https://www.anchorterminal.com/compare/pplx-decider-flash-vs-vela.md)
- [pplx-decider vs kettei](https://www.anchorterminal.com/compare/pplx-decider-vs-sqwish-kettei.md)
- [pplx-decider vs Vela 2.0](https://www.anchorterminal.com/compare/pplx-decider-vs-vela.md)
- [ScaleDown vs kettei](https://www.anchorterminal.com/compare/scaledown-vs-sqwish-kettei.md)
- [ScaleDown vs Vela 2.0](https://www.anchorterminal.com/compare/scaledown-vs-vela.md)
- [SPEV vs kettei](https://www.anchorterminal.com/compare/sprag-spev-vs-sqwish-kettei.md)
- [SPEV vs Vela 2.0](https://www.anchorterminal.com/compare/sprag-spev-vs-vela.md)
- [kettei vs Strands Decider 2B](https://www.anchorterminal.com/compare/sqwish-kettei-vs-strands-decider.md)
- [kettei vs Jev](https://www.anchorterminal.com/compare/sqwish-kettei-vs-typesafe-jev.md)
- [Strands Decider 2B vs Vela 2.0](https://www.anchorterminal.com/compare/strands-decider-vs-vela.md)
- [Jev vs Vela 2.0](https://www.anchorterminal.com/compare/typesafe-jev-vs-vela.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp