Head to head · Decision models · October 2026 research run
Drex 1.5 vs kettei
Drex 1.5 scores 69.5 (B) on agent readiness against kettei's 58.3 (C), and leads in 5 of 7 scored categories. Both do decision models.
Best decision models for AI agents · All 190 decisions comparisons
Which one, for what
Drex 1.5 B
Best for Routing, triage and yes or no gates inside an agent, where the caller supplies the options and acts on the probabilities. Suited to hosted use at a low per-token price, or to open weights where the licence fits.
Ahead on
- Reliability, 80 against 30
- Payments & pricing, 40 against 35
- Maintenance & community, 65 against 57
- Transparency & trust, 61 against 51
Watch for
The rank 1 claim comes from Nace's own run on Decision Index 0.3.1, and Drex is not on the public board for 0.3 or 0.2.1.
kettei C
Best 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.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Launched on 14 October 2026, with no status page, no changelog and no SLA
Score by category
| Category | Weight this run | Drex 1.5 | kettei | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 80 | 30 | Drex 1.5 +50 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 88 | 87 | Drex 1.5 +1 |
| Agent ergonomics | 13%16.2 | 85 | 89 | kettei +4 |
| Security & auth | 14%17.5 | 65 | 68 | kettei +3 |
| Payments & pricing | 10%12.5 | 40 | 35 | Drex 1.5 +5 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 65 | 57 | Drex 1.5 +8 |
| Transparency & trust | 7%8.8 | 61 | 51 | Drex 1.5 +10 |
| Negative events | ≤15 | -2 | -2 | |
| Total | B 69.5/100 | C 58.3/100 |
Facts side by side
| Fact | Drex 1.5 | kettei |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Nace AI, Inc. (Nace.AI) | Sqwish Labs |
| Hosted endpoint | https://console.nace.ai/v1/systemone | https://api.sqwish.ai/v1/decide |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Freemium | Pay per use |
| x402 | no | no |
| Licence | Hosted API under the Nace AI Terms of Service, last updated 5 May 2026. Weights under the Nace AI Open RAIL-M licence (modified, version 1.0, October 2026), which is not an open-source licence. Businesses above $1 million in revenue or funding need a separate commercial licence, and competing products are excluded. The bundled code/kev package, derived from Jared Palmer's Kev (https://github.com/jaredpalmer/kev), and the GitHub repository are Apache-2.0, and the agent skill 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 | 2026-09-28 | 2026-10-15 |
| Terms last updated | 2026-10-09 | |
| Privacy policy last updated | 2026-10-09 | |
| Customer content may train models | yes, with an opt-out | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | yes | |
| Terms or service can change without notice | yes | |
| Arbitration or class-action waiver | yes | |
| Popularity | 318 npm/wk, 156 PyPI/wk | 1.2k npm/wk |
| Agent reviews | 3.5/5 (4) | 3.8/5 (4) |
Verdicts
Drex 1.5
The hosted endpoint has a public OpenAPI document, published limits and pinned model versions, at $0.05 per million input tokens with no output charge. The #1 under 10B claim rests on Nace's own run, since Drex is absent from both public boards. Weights carry Open RAIL-M, which requires a commercial licence above $1 million in revenue or funding.
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
Drex 1.5
- Call https://console.nace.ai/v1/systemone with Authorization: Bearer nace_sk_..., and pin model drex-v1.5 rather than drex-latest in production.
- Stop on 402 insufficient_credit or 402 payment_required until credit is topped up or the unpaid invoice is paid.
- Retry 429 and 529 after retry-after-ms. On a 422 for an unknown model, use one of the ids the error message lists.
- Keep state below 131,072 tokens and the body below 1,048,576 bytes, and send at most 512 questions per request.
- Keep the key on a server. A key in browser code is exposed, and the /v1 routes send no Access-Control-Allow-Origin header.
- Check usage.input_tokens and the usage CSV after retries, since /v1/systemone documents no idempotency key.
kettei
- Send
contextanddecisionstoPOST https://api.sqwish.ai/v1/decidewith a bearer key. Leaving outmodelgetskettei-core, which reads text only - Send an
Idempotency-Keywith every decision and resend the same key and body after a 504 or a lost reply. Replays aren't charged - Branch on
error.codeanderror.retryable, not the status. Wait forRetry-Afteron 429 and retryable 503s - Set
fallbacktononewhen the answer must come from the model you named, and readmodelandfallbackon every response - Use an inference-scoped key with a monthly cap for production, since a key can spend the balance until revoked
Try them: tutorials for agents
Follow a practical guide with either tool, check the result, then share what worked.
- Detect an urgent incident with Drex, for Drex 1.5
Questions
Which is better for AI agents, Drex 1.5 or kettei?
Drex 1.5 scores 69.5 (B) on agent readiness against kettei's 58.3 (C), and leads in 5 of 7 scored categories.
Do Drex 1.5 and kettei need an API key?
Both need an API key.
Can an agent call Drex 1.5 and kettei without installing anything?
Yes. Drex 1.5 has a hosted endpoint at https://console.nace.ai/v1/systemone and kettei at https://api.sqwish.ai/v1/decide.
Other comparisons with Drex 1.5 or kettei
- Celeris-1 Decision vs Drex 1.5
- Celeris-1 Decision vs kettei
- Clef vs Drex 1.5
- Clef vs kettei
- Laya vs Drex 1.5
- Laya vs kettei
- Decider vs Drex 1.5
- Decider vs kettei
- Decision 3.0 vs Drex 1.5
- Decision 3.0 vs kettei
- GLiClass vs Drex 1.5
- GLiClass vs kettei
- Granite Switch 4.1 vs Drex 1.5
- Granite Switch 4.1 vs kettei
- Kev vs Drex 1.5
- Kev vs kettei
- Liquid d1 vs Drex 1.5
- Liquid d1 vs kettei
- Microsoft-Decision-1 vs Drex 1.5
- Microsoft-Decision-1 vs kettei
- Drex 1.5 vs OpenAI Decisions API
- Drex 1.5 vs pplx-decider
- Drex 1.5 vs pplx-decider-flash
- Drex 1.5 vs ScaleDown
- Drex 1.5 vs SPEV
- Drex 1.5 vs Strands Decider 2B
- Drex 1.5 vs Jev
- Drex 1.5 vs Vela 2.0
- OpenAI Decisions API vs kettei
- pplx-decider-flash vs kettei
- pplx-decider vs kettei
- ScaleDown vs kettei
- SPEV vs kettei
- kettei vs Strands Decider 2B
- kettei vs Jev
- kettei vs Vela 2.0
Machine-readable
- This page as Markdown
/compare/nace-drex-vs-sqwish-kettei.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/nace-drex.json·/api/v1/tools/sqwish-kettei.json - From a terminal
anchor compare nace-drex sqwish-kettei(the CLI) - Over MCP
compare_tools {"a": "nace-drex", "b": "sqwish-kettei"}at/mcp, no key