Publish time
2026/1/1Model Series
Input type
Output type
Context Window
163,840Max Output Length
163,840Input Price
¥2 / 1M tokensOutput Price
¥8 / 1M tokens【deepseek官方】deepseek v3版本模型。DeepSeek-V3 为自研 MoE 模型，671B 参数，激活 37B，在 14.8T token 上进行了预训练。DeepSeek-V3 多项评测成绩超越了 Qwen2.5-72B 和 Llama-3.1-405B 等其他开源模型，并在性能上和世界顶尖的闭源模型 GPT-4o 以及 Claude-3.5-Sonnet 不分伯仲。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
0.13s
Throughput
10.47tps
Uptime
100.00%
Provider Model
deepseek/deepseek/deepseek-chat
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Request Log Collection
-
Distillable
-
Total Context
163,840
Max Output
163,840
Input Price
¥2 / 1M tokens
Output Price
¥8 / 1M tokens
TTFT
0.74s
Throughput
59.41tps
Uptime
95.00%
Provider Model
st/deepseek/deepseek-v4-flash
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
¥0.8 / 1M tokens
Output Price
¥1.6 / 1M tokens
Compare different providers across Zhinao API
34.98 tok/s
0.18 s
Uptime for deepseek/deepseek-chat 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-chat",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);