d3-flash

POST /v1/systemone model: d3-flash

d3-flash is the 9B model of Decision 3.0, the decision models of vLLM Semantic Router, built on Qwen3.5-9B. It takes the same requests and returns the same replies as d3, with the same 32,768-token input limit, about three times faster on this deployment and a little less accurate. Read the d3 page for the request fields, question types, response and errors.

At a glance


Endpoint	`POST /v1/systemone`
Input	a `state` (text or any JSON), plus optional images and videos
Output	one answer per question, with a probability for every option
Question types	`choice`, `noul`, `score`
Input limit	32,768 tokens per question; longer requests are refused, not truncated
Latency	about 0.1 s for a three-question text request, one at a time
Streaming	❌
Billing	per input token, reported as `usage.input_tokens`; `output_tokens` is always `0`
Stability	`experimental`
License	Apache-2.0

Example

curl https://developer.amd.com.cn/radeon/api/v1/systemone \
  -H "Authorization: Bearer $RADEON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "d3-flash",
    "state": "Write a Python function that merges two sorted lists.",
    "questions": {
      "kind": {"type": "choice", "instructions": "What kind of work is this?",
               "criteria": {"code": "Writing or fixing code", "math": "Mathematics", "chat": "Anything else"}},
      "reasoning": {"type": "noul", "instructions": "Does answering this need multi-step reasoning?"}
    }
  }'