为什么选它
- 适合大规模批量推理
- 上游 MIT 许可
DeepSeek
deepseek-v3
DeepSeek V3
适合大规模对话与批处理的稳定版 DeepSeek 通用模型。
公开模型详情Dense Transformer
参数规模
671B
上下文
160K
最大输出
64K
许可证
MIT
TTFT
160ms
吞吐
120 tok/s
价格与差价
层级标准缓存SiliconFlow节省
在线调用$0.08 / $0.28$0.028$0.27 / $1.0070%
批处理$0.04 / $0.14$0.028$0.27 / $1.0070%
快速开始
OpenAI 兼容接口，切换 base_url 即可。
Python
from openai import OpenAI
client = OpenAI(
base_url="https://api.luminapath.tech/v1",
api_key="BATCHIN_API_KEY"
)
resp = client.chat.completions.create(
model="deepseek-v3",
messages=[{"role": "user", "content": "Summarize why this model is a fit for my workload."}]
)
print(resp.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.luminapath.tech/v1",
apiKey: process.env.BATCHIN_API_KEY,
});
const resp = await client.chat.completions.create({
model: "deepseek-v3",
messages: [{ role: "user", content: "Summarize why this model is a fit for my workload." }],
});
console.log(resp.choices[0]?.message?.content);cURL
curl https://api.luminapath.tech/v1/chat/completions \
-H "Authorization: Bearer $BATCHIN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v3",
"messages": [{"role":"user","content":"Summarize why this model is a fit for my workload."}]
}'规格与行为
架构
Dense Transformer
厂商家族
DeepSeek
上下文
160K
最大输出
64K
适用场景
chat
batch
相关模型
返回模型中心
