Call POST /compatible-mode/v1/systemone to use the Bailian decision model (decision-model-preview), which returns classification, scoring, and yes/no decisions with full probability distributions and confidence in a single forward pass, without generating text. Suitable for high-frequency structured decisions such as ticket routing, content moderation, agent routing, and result verification.
Prerequisites
You have created an API Key and set it as the environment variable DASHSCOPE_API_KEY. For more information, see Configure an API key in environment variables.
Request
Protocol: TypeSafe System One (POST /compatible-mode/v1/systemone)
A single request carries the business state and several typed questions (choice / noul / score). The model returns the decision result and probability distribution for each question in one forward pass, with choice and score additionally returning confidence, and does not generate text, so latency and cost are independent of output length.
Endpoint
Replace {WorkspaceId} with your workspace ID. See Regions and endpoints.
Region | Endpoint |
|---|---|
Singapore |
|
China (Beijing) |
|
Request Parameters
Content-Type ·String · Header · RequiredRequest type: application/json.Authorization · String · Header · RequiredAPI key, in the format: Bearer $DASHSCOPE_API_KEY.model · String · Body · RequiredModel name: decision-model-preview.state · String / Object / Array · Body · RequiredThe business state to make decisions on: ticket text, a conversation, or a structured object (objects are serialized before being sent to the model).questions · Object · Body · RequiredA map of questions. The key is a caller-defined question id; the value is a question object with the following fields.Question object properties
Question object properties
type ·
String · RequiredQuestion type:choice: single choicenoul: yes/noscore: ordinal scale
String · OptionalQuestion description or judgment criteria.criteria · Object / Array · Depends on typechoice: a map of option name → option description (1–255 items; providing all options and anotherfallback is recommended).noul: optional{"true":…, "false":…}descriptions.score: an array of level descriptions from low to high (2–10 levels; 3–7 clearly distinguishable levels recommended).
- No hard limit on the number of questions (recommended: ≤ 16; latency grows near-linearly with the number of questions).
choiceoptions: ≤ 255.scorelevels: 2–255 (3–7 recommended).- Context: maximum 65536 tokens; overlong
stateis rejected or truncated.
Request Examples
The Python examples use the TypeSafe SDK (typesafe-sdk) with base_url pointing to the Bailian gateway. The SDK automatically appends /v1/systemone and parses the response. Install: pip install typesafe-sdk.- Ticket routing
- Yes/no decision
A single request handles three decisions at once: team assignment (
choice), escalation (noul), and severity (score). The example below uses the Singapore region.Response Parameters
model ·StringModel name echoed back.request_id · StringRequest ID, for troubleshooting.answers · ObjectA map of answers. The key corresponds to the question id in the request; the value is an answer object with the following fields.Answer object properties
Answer object properties
type ·
StringMatches the question type (choice / noul / score).choice · StringFor choice: the selected option name.noul · FloatFor noul: P(yes), where 0 = no and 1 = yes.score · FloatFor score: the probability-weighted expectation of the level index, which can fall between two levels (e.g. 1.43).probabilities · ObjectThe probability of each option / level (sums to 1).confidence · FloatThe confidence of the answer (returned for choice / score).legend · ObjectFor score: a map of level index → level description.ObjectMetering information:input_tokens(Integer): number of input tokens.
FloatServer-side latency (milliseconds).