Publish time
-Model Series
DeepSeekInput type
Output type
Input Price
¥4 / 1M tokensOutput Price
¥16 / 1M tokensCache Write Price
¥5 / 1M tokensCache Read Price
¥0.4 / 1M tokensContext Window
128,000Max Output Length
31,000【360在阿里云部署版】DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力。在数学、代码、自然语言推理等任务上，性能比肩 OpenAI o1 正式版。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
No data
Throughput
30.57tps
Uptime
100.00%
Provider Model
360/huaweiyun-deepseek-r1
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Total Context
65,536
Max Output
31,000
Input Price
¥4 / 1M tokens
Output Price
¥16 / 1M tokens
Cache Write
¥5 / 1M tokens
Cache Read
¥0.4 / 1M tokens
TTFT
0.98s
Throughput
49.48tps
Uptime
99.00%
Provider Model
huaweicloud/deepseek/deepseek-v4-flash
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
1,000,000
Max Output
384,000
Input Price
¥1 / 1M tokens
Output Price
¥2 / 1M tokens
Cache Write
¥1.25 / 1M tokens
Cache Read
¥0.02 / 1M tokens
TTFT
0.53s
Throughput
20.47tps
Uptime
94.00%
Provider Model
paratera/deepseek-r1
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Total Context
65,536
Max Output
31,000
Input Price
¥4 / 1M tokens
Output Price
¥16 / 1M tokens
Cache Write
¥5 / 1M tokens
Cache Read
¥0.4 / 1M tokens
TTFT
No data
Throughput
No data
Uptime
100.00%
Provider Model
qiniu/deepseek-r1
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
65,536
Max Output
8,096
Input Price
¥4 / 1M tokens
Output Price
¥16 / 1M tokens
Cache Write
¥5 / 1M tokens
Cache Read
¥0.4 / 1M tokens
TTFT
No data
Throughput
No data
Uptime
20.00%
Provider Model
volcengine/deepseek-r1
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Total Context
65,536
Max Output
8,096
Input Price
¥4 / 1M tokens
Output Price
¥16 / 1M tokens
Cache Write
¥5 / 1M tokens
Cache Read
¥0.4 / 1M tokens
TTFT
No data
Throughput
No data
Uptime
94.00%
Provider Model
baidu/deepseek-r1-250528
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Total Context
65,536
Max Output
8,096
Input Price
¥2 / 1M tokens
Output Price
¥8 / 1M tokens
Cache Write
¥2.5 / 1M tokens
Cache Read
¥0.2 / 1M tokens
TTFT
No data
Throughput
No data
Uptime
No data
Provider Model
sophnet/deepseek-r1
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Total Context
4,096
Max Output
2,048
Input Price
¥4 / 1M tokens
Output Price
¥16 / 1M tokens
Cache Write
¥5 / 1M tokens
Cache Read
¥0.4 / 1M tokens
TTFT
1.32s
Throughput
90.59tps
Uptime
100.00%
Provider Model
tencent/deepseek/deepseek-v4-flash
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
1,000,000
Max Output
384,000
Input Price
¥3 / 1M tokens
Output Price
¥9 / 1M tokens
Cache Write
¥3.75 / 1M tokens
Cache Read
¥0.3 / 1M tokens
TTFT
No data
Throughput
13.50tps
Uptime
No data
Provider Model
guizhoumobile/deepseek-r1
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Total Context
65,536
Max Output
8,096
Input Price
¥4 / 1M tokens
Output Price
¥16 / 1M tokens
Cache Write
¥5 / 1M tokens
Cache Read
¥0.4 / 1M tokens
TTFT
1.62s
Throughput
51.99tps
Uptime
100.00%
Provider Model
alibaba/deepseek/deepseek-v4-flash
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
1,000,000
Max Output
384,000
Input Price
¥3 / 1M tokens
Output Price
¥9 / 1M tokens
Cache Write
¥3.75 / 1M tokens
Cache Read
¥0.3 / 1M tokens
Compare different providers across Zhinao API
43.52 tok/s
0.14 s
Uptime for deepseek-r1 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-r1",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);