# Decision Model Preview

Model id on AIHubMix: `decision-model-preview`
Create an API key: https://console.aihubmix.com/?utm_source=llms-agent&utm_medium=model-llms

> Alibaba Cloud has launched the decision model decision-model-preview. This structured decision model is designed for high-frequency business judgments; it can concurrently perform classification, binary decisions, and scoring based on text or business state, and returns probability distributions and confidence levels. It is suitable for scenarios such as ticket routing, content moderation, agent routing, and result verification. Free for a limited time.

- Developer: Qwen
- Context window: 64,000 tokens
- Release date: 2026-09-24
- Pricing: free tier / see model page

**This is a decision model, not a chat model.** It has no `/v1/chat/completions`
endpoint — sending `messages` to it returns 404. You send a `state` (the text to judge)
plus a map of typed `questions`, and get typed answers back.

## Endpoints (base URL: https://aihubmix.com)

- `POST /v1/systemone` — structured decision (`Authorization: Bearer $AIHUBMIX_API_KEY`)

## Request

`{model, state, questions}`. Each entry in `questions` is named by you and has a
`type` of `noul`, `choice` or `score`, an `instructions` string, and — for the
latter two — a `criteria` whose **shape differs by type**:

- `noul` — no `criteria`. Returns the probability that `instructions` holds.
- `choice` — `criteria` is an **object**: option name → what that option means. Returns one option name.
- `score` — `criteria` is an **array**: the ordered levels, lowest first. Returns the level index.

Passing an array where an object is expected (or vice versa) is an HTTP 400, not a
coercion — the two shapes are not interchangeable.

## Example

```bash
# Structured decision: POST /v1/systemone — every question is evaluated in parallel and in
# isolation against the same state, and comes back typed. No text generation, nothing to parse.
# The answers{} map is keyed by your own question names; each answer holds its value under a
# key named after its type:
#   noul   -> { type, noul }                                      probability of "yes", 0..1
#   choice -> { type, choice, probabilities, confidence }          choice is one of your criteria keys
#   score  -> { type, score, legend, probabilities, confidence }   legend maps level index -> description
# usage carries input_tokens / output_tokens.
curl https://aihubmix.com/v1/systemone \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -d '{
    "model": "decision-model-preview",
    "state": "Hi, I have been trying to connect my Stripe account for 3 days and it keeps failing. I am losing sales. Please help ASAP.",
    "questions": {
      "department": {
        "type": "choice",
        "instructions": "Which team should handle this",
        "criteria": {
          "billing": "Payment or subscription issues",
          "technical": "Bugs or integration problems",
          "sales": "Pricing or account questions"
        }
      },
      "frustration": {
        "type": "score",
        "instructions": "How frustrated the customer appears",
        "criteria": [
          "Calm, just stating facts",
          "Frustrated but civil",
          "Very angry, strong language"
        ]
      },
      "is_urgent": {
        "type": "noul",
        "instructions": "The message conveys urgency or time-sensitivity"
      }
    }
  }'
```

## Response

Always a single JSON object — no streaming, no text to parse. `answers` is keyed by
**your own** question names, and each answer carries its value under a key named after
its type:

```json
{
  "model": "jev-1.13.0",
  "answers": {
    "is_urgent":   {"type":"noul","noul":0.99},
    "department":  {"type":"choice","choice":"billing","confidence":0.53,"probabilities":{"billing":0.69,"sales":0.0,"technical":0.31}},
    "frustration": {"type":"score","score":1.0,"confidence":1.0,"legend":{"0":"Calm, just stating facts","1":"Frustrated but civil","2":"Very angry, strong language"},"probabilities":{"0":0.0,"1":1.0,"2":0.0}}
  },
  "usage": {"input_tokens":424,"output_tokens":73}
}
```

- `noul` — probability in `0..1` that the statement holds. No threshold is baked in; pick your own.
- `choice` — one of **your** `criteria` keys, plus the full probability distribution over them.
- `score` — the level **index**, `0`-based, counted from your `criteria` array (serialized as a number, so `1` may arrive as `1.0`). `legend` echoes your levels back so the index is readable without holding on to the request.
- `confidence` accompanies `choice` and `score` only; `noul` is already a probability.
- `model` echoes the resolved upstream build (`jev-latest` resolves to a pinned version here), which is not the id you send.

Every question is evaluated in parallel and in isolation against the same `state`, so
answers never influence each other and question order carries no meaning.

## Errors

Error responses carry a `tid` (trace id) — include it when contacting support. Reference: https://docs.aihubmix.com/en/FAQs/HTTP-Codes.md

- 400 — parameter error; most are passed through from the upstream provider (media: `prompt_missing`, `size_not_supported`, `n_not_within_range`, …)
- 401 — missing `Authorization` header, or the key is invalid/expired
- 403 — `insufficient_user_quota` (top up at https://console.aihubmix.com/?utm_source=llms-agent&utm_medium=model-llms), account suspended, or this key is not allowed to use this model
- 429 — rate limited; back off and retry
- 503 — no channel can serve the request (check the model id and your access), or the upstream provider is throttling; retry later

## More

- Model page: https://aihubmix.com/model/decision-model-preview
- Try in browser: https://playground.aihubmix.com/?model=decision-model-preview
- Full parameter schema: follow `https://aihubmix.com/model-data/index.json` — find this id and fetch its `path` (filenames are content-addressed; do not compose them by hand)
- Generate runnable code programmatically: npm `@aihubmix/codegen` — `generateDecisionCode()` renders the snippet above in 7 languages, and `buildDecisionBody()` is the same function the Playground calls to build the request it actually sends, so generated snippets and real requests cannot diverge
- Site index for agents: https://aihubmix.com/llms.txt · Onboarding: https://aihubmix.com/agents.md

---

Canonical version of this document: https://aihubmix.com/model/decision-model-preview/llms.txt