Publish time
-Model Series
Input type
Output type
Context Window
128,000Max Output Length
8,096Input Price
¥4 / 1M tokensOutput Price
¥12 / 1M tokens【虚拟模型】DeepSeek-V3.1 是深度求索全新推出的混合推理模型，支持思考与非思考2种推理模式，较 DeepSeek-R1-0528 思考效率更高。经 Post-Training 优化，Agent 工具使用与智能体任务表现大幅提升。支持 128k 上下文窗口，输出长度支持最大 64k tokens。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
No data
Throughput
26.97tps
Uptime
100.00%
Provider Model
huaweicloud/deepseek-v3.1
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Request Log Collection
-
Distillable
-
Total Context
65,536
Max Output
31,000
Input Price
¥1 / 1M tokens
Output Price
¥4 / 1M tokens
TTFT
0.01s
Throughput
8.04tps
Uptime
100.00%
Provider Model
qiniu/deepseek-v3.1
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Request Log Collection
-
Distillable
-
Total Context
65,536
Max Output
8,096
Input Price
¥2 / 1M tokens
Output Price
¥6 / 1M tokens
Compare different providers across Zhinao API
4.50 tok/s
No data
Uptime for deepseek-v3.1 across all providers
Zhinao API normalizes requests and responses across providers for you
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.360.cn/v1",
apiKey: process.env.ZHINAO_API_KEY,
});
const response = await client.chat.completions.create({
model: "deepseek-v3.1",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);