[ plus ]
Plus
R$ 110 per month
or R$ 1,100 per year, with 2 months free
- Decisions per month:
- 3,600,000
- Overage:
- R$ 0.030 per 1,000
The decision model by Zyrex. It takes a context. It returns typed decisions, each with measured confidence and the full spectrum. It doesn't write text.
Measured on Zyrex's own answer key on 2026-09-23, on short texts in Portuguese. See the numbers.
Pick a message. Iryx opens each decision as a spectrum, scores the options and keeps the most likely one. The band (low, medium or high) is the confidence cut Zyrex recommends: on low, check before you act.
POST /v1/decideA demo with ready-made answers: this page doesn't call the model. The sneaker exchange is a real test, run on 2026-09-24 with a made-up message in Portuguese; the test kept the chosen value of each decision, and the rest of the spectrum shows as a sum. The other two cases are illustrative examples. The band is computed on this page, with the recommended cuts; the API returns the value, the confidence and the spectrum.
[ benchmarks · own answer key ]
Four measures, one answer key. Where Iryx does well and where it still misses the most.
Accuracy on each test, on the same scale. The blind tests bring subjects Iryx never saw. The second one is where it still misses the most, and the chart shows it.
Each pixel is one complete request, with ~3 decisions, at the time measured through the API on the same machine. Over the internet, add the network time.
| Measure | Iryx | N |
|---|---|---|
| Math, exact answer | 100% | 33 |
| Main test | 82% | 225 |
| Blind test 1, new domains | 86% | 100 |
| Blind test 2, other new domains | 73% | 100 |
| Response, median per request | ~74 ms | 200 |
How to read it. Text has no neutral answer key: we use Zyrex's own. The 33 math questions are part of the main test, and there the truth is absolute. The blind tests bring subjects Iryx never saw; the second is the hardest for it today. All measured on 2026-09-23, on short texts in Portuguese.
Billed per decision, never per token. No free plan: Try it now shows the product without an account. Pay yearly and get 2 months free. Prices in Brazilian reais.
[ plus ]
R$ 110 per month
or R$ 1,100 per year, with 2 months free
[ ultra ]
R$ 490 per month
or R$ 4,900 per year, with 2 months free
[ business ]
R$ 1,990 per month
or R$ 19,900 per year, with 2 months free
[ dedicated business ]
from R$ 4,900 per month
For high volume or a setup of your own. We'll work out the format together.
Talk to us↗[ pay as you go ]
R$ 0.033 per 1,000 decisions
No monthly fee. Minimum top-up of R$ 50.
Talk to us↗Prices in Brazilian reais (R$). The unit is the decision: a request with three decisions counts as three. Each plan's overage costs that plan's price per 1,000. Business volume is confirmed when we talk.
A direction, not a measured result.
[ brand consistency ]
Iryx checking whether a piece follows its design system (color, type, spacing), with a confidence number.
[ art direction at scale ]
Small, fast decisions that keep one aesthetic across thousands of pieces.
[ second opinion ]
Software agents checking with Iryx before they act, with the confidence band saying when to stop and ask a person.
How Iryx was made:
The dashboard isn't live yet. For now, everything starts by email.
Tell us what you want to decide, and at what volume.
Plus, Ultra, Business or pay as you go. We'll help you estimate your decisions per month.
With your key, one POST /v1/decide request carries the context and the decisions. Back come the value, the confidence and the spectrum of each one.
A decision model. It takes a context and closed questions (pick one option, yes or no, a level on a scale) and returns each answer with measured confidence and the full spectrum. It doesn't write text.
EYE-riks. Spelled with a Y: I, R, Y, X.
Each question answered. A request with three decisions counts as three. Billing is per decision, never per token.
No. Try it now, on this page, shows the product with no account and no credit. To use it for real, plans start at R$ 110 per month, and pay as you go starts with a R$ 50 top-up.
On subjects it has never seen. On blind test 2, with four new domains, it scored 73% (100 questions), against 82% on the main test. There, more decisions land in the low band: decide together, looking at the runner-up.
Today, the API doesn't store the context or the answers: it reads, decides in memory and replies. The log for each request keeps only operational data: the time, the method, the route, the status, the request id, the number of decisions and the duration, plus the error type when something fails. The hosted service isn't live yet; its rules will be in the terms of use before the first customer.
The API takes any text. The numbers on this page were measured on short texts in Portuguese; in English, quality hasn't been measured yet.
Classified.