A structured decision model designed for high-frequency business decisions. It performs classification, yes-or-no decisions, and scoring in parallel based on text or business context, returning probability distributions and confidence scores for scenarios such as ticket routing, content moderation, agent routing, and result validation.
Inference Service Provider
The inference service provider for decision-model-preview is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | Text (structured decision result) |
Model Experience | Unsupported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 65,536 | Max Output Length | 0 |
Context Window | 65,536 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
Singapore
| Billing Item | Price (USD) | Unit |
|---|---|---|
Limited-time free | ||
China (Beijing)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Limited-time free | ||
Rate Limits
Singapore
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 1,200 |
TPM (Tokens Per Minute) | 2,000,000 |
China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 1,200 |
TPM (Tokens Per Minute) | 2,000,000 |
Calling Method
For the calling protocol, request/response parameters, and code examples, see Decision Model API.