d3-flash
POST
/v1/systemone
model:
d3-flash
d3-flash 是 vLLM Semantic Router 的决策模型系列 Decision 3.0 中的 9B 模型,基于 Qwen3.5-9B。它接受的请求、返回的响应都和 d3 相同,输入上限同为 32,768 token,在本部署上快约三倍,准确率略低。请求字段、问题类型、响应和错误请看 d3 页面。
| 端点 | POST /v1/systemone |
| 输入 | state(文本或任意 JSON),可选图片和视频 |
| 输出 | 每个问题一个答案,附每个选项的概率 |
| 问题类型 | choice、noul、score |
| 输入上限 | 每个问题 32,768 token;超长请求会被拒绝,不会截断 |
| 延迟 | 三个问题的文本请求逐个发送约 0.1 秒 |
| 流式 | ❌ |
| 计费 | 按输入 token,对应 usage.input_tokens;output_tokens 恒为 0 |
| 稳定性 | experimental |
| 许可证 | Apache-2.0 |
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?"} } }'