Publish time
2025/1/20Model Series
DeepSeekInput type
Output type
Input Price
¥1.5 / 1M tokensOutput Price
¥6 / 1M tokensCache Write Price
¥1.875 / 1M tokensCache Read Price
¥0.15 / 1M tokensContext Window
65,536Max Output Length
8,096DeepSeek-R1-Distill 模型是在开源模型的基础上通过微调训练得到的，训练过程中使用了由DeepSeek-R1生成的样本数据。DeepSeek-R1是由深度求索推出的推理大模型。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
1.76s
Throughput
27.36tps
Uptime
100.00%
Provider Model
guizhoumobile/deepseek-r1-distill-qwen-32b
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Total Context
65,536
Max Output
8,096
Input Price
¥1.5 / 1M tokens
Output Price
¥6 / 1M tokens
Cache Write
¥1.875 / 1M tokens
Cache Read
¥0.15 / 1M tokens
Compare different providers across Zhinao API
27.36 tok/s
1.76 s
Uptime for deepseek/deepseek-r1-distill-qwen-32b 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/deepseek-r1-distill-qwen-32b",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);