Publish time
2026/4/24Model Series
DeepSeekInput type
Output type
Context Window
1,000,000Max Output Length
384,000Input Price
¥3 / 1M tokensOutput Price
¥6 / 1M tokensDeepSeek-V4 拥有百万字超长上下文，在 Agent 能力、世界知识和推理性能上均实现国内与开源领域的领先。 相比前代模型，DeepSeek-V4-Pro 的 Agent 能力显著增强。在 Agentic Coding 评测中，V4-Pro 已达到当前开源模型最佳水平，并在其他 Agent 相关评测中同样表现优异。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
1.69s
Throughput
26.03tps
Uptime
99.00%
Provider Model
deepseek/deepseek/deepseek-v4-pro
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Request Log Collection
ZDR Supported
Distillable
Yes
Total Context
1,000,000
Max Output
384,000
Input Price
¥3 / 1M tokens
Output Price
¥6 / 1M tokens
TTFT
2.23s
Throughput
21.55tps
Uptime
93.00%
Provider Model
st/deepseek/deepseek-v4-pro
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Request Log Collection
ZDR Supported
Distillable
Yes
Total Context
1,000,000
Max Output
384,000
Input Price
¥9.6 / 1M tokens
Output Price
¥19.2 / 1M tokens
Compare different providers across Zhinao API
22.31 tok/s
1.61 s
Uptime for deepseek/deepseek-v4-pro 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-v4-pro",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);