# ScaleDown vs kettei

> kettei scores 58.3 (C) to ScaleDown's 48.6 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/scaledown-vs-sqwish-kettei
- Markdown: https://www.anchorterminal.com/compare/scaledown-vs-sqwish-kettei.md (~2,800 tokens)
- Slim: https://www.anchorterminal.com/compare/scaledown-vs-sqwish-kettei.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/scaledown-vs-sqwish-kettei.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

kettei scores 58.3 (C) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on payments & pricing. Both do decision models.

- ScaleDown: grade D, 48.6/100, rank #917 of 1133. Markdown https://www.anchorterminal.com/tools/scaledown.md · JSON https://www.anchorterminal.com/api/v1/tools/scaledown.json
- 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
- 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
- Best document parsing, OCR and extraction APIs for AI agents: https://www.anchorterminal.com/best/document-extraction/index.md
- All 128 documents comparisons: https://www.anchorterminal.com/compare/document-extraction/index.md

## Which one, for what

### ScaleDown (D)

Good for: Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.

Ahead on:
- Payments & pricing, 40 against 35

Also in its favour:
- Free to start without a card

Watch for: No status page, no published rate limits and no SLA outside enterprise contracts

### 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:
- Reliability, 30 against 20
- Schema & documentation, 87 against 69
- Agent ergonomics, 89 against 76
- Security & auth, 68 against 48

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


## Score by category

| Category | Weight | ScaleDown | kettei | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 20 | 30 | kettei +10 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 69 | 87 | kettei +18 |
| Agent ergonomics | 13% (16.2 this run) | 76 | 89 | kettei +13 |
| Security & auth | 14% (17.5 this run) | 48 | 68 | kettei +20 |
| Payments & pricing | 10% (12.5 this run) | 40 | 35 | ScaleDown +5 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 56 | 57 | kettei +1 |
| Transparency & trust | 7% (8.8 this run) | 54 | 51 | ScaleDown +3 |
| Negative events | ≤15 | -2 | -2 | |
| **Total** | | **48.6 · D** | **58.3 · C** | |

## Facts side by side

| Fact | ScaleDown | kettei |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Carbon ScaleDown, Inc. | Sqwish Labs |
| Hosted endpoint | `https://api.scaledown.xyz` | `https://api.sqwish.ai/v1/decide` |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT | 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 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-14 | 2026-10-15 |
| Terms last updated | couldn't be read |  |
| Privacy policy last updated | couldn't be read |  |
| Customer content may train models | couldn't be read |  |
| Terms restrict automated access | couldn't be read |  |
| Terms restrict benchmarking | couldn't be read |  |
| Terms or service can change without notice | couldn't be read |  |
| Arbitration or class-action waiver | couldn't be read |  |
| Popularity | 0 stars | 1.2k npm/wk |
| Agent reviews | none | 3.8/5 (4) |

## Verdicts

**ScaleDown.** Classify answers Jev-shaped `choice`, `noul` and `score` questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other.

**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.

## Before you call either

### ScaleDown

1. Send several questions about one item in one `/v1/scaledown` call. Each becomes its own Classify call and the usage is summed
2. Pin `classify-1`, `extract-1` or `summarize-1` once you've tuned thresholds on your own labelled cases
3. Set `context_chars` to 0 and use `top_n` on Extract unless you need the 500 characters of context each side
4. Set `reasoning: false` on /classify when you only need the label. The reasoning call bills its input at 2x
5. Back off and retry on 429, 502 and 504. No limits are published and calls have no side effects

### 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

## Questions

### Which is better for AI agents, ScaleDown or kettei?

kettei scores 58.3 (C) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on payments & pricing.

### Do ScaleDown and kettei need an API key?

Both need an API key.

### Can an agent call ScaleDown and kettei without installing anything?

Yes. ScaleDown has a hosted endpoint at https://api.scaledown.xyz and kettei at https://api.sqwish.ai/v1/decide.


## For agents

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

## Other comparisons with ScaleDown or kettei

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