Publish time
2026/8/21Model Series
DeepSeekInput type
Output type
Input Price
¥3 / 1M tokensOutput Price
¥9 / 1M tokensCache Write Price
¥3.75 / 1M tokensCache Read Price
¥0.3 / 1M tokensContext Window
1,000,000Max Output Length
384,000deepseek-v4-flash-vision-exp 模型支持在文本之外输入图片，你可以让模型描述图片、识别截图中的文字、分析图表等。 支持的图片格式：JPEG、PNG、GIF、WebP。格式由文件实际内容判断，而非文件名或声明的 MIME 类型。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
1.03s
Throughput
115.98tps
Uptime
100.00%
Provider Model
deepseek/deepseek/deepseek-v4-flash-vision-exp
Supported Parameters
Recent Uptime
Reasoning
Toggleable
Supported Response Formats
Total Context
1,000,000
Max Output
384,000
Input Price
¥2 / 1M tokens
Output Price
¥8 / 1M tokens
Cache Write
¥2.5 / 1M tokens
Cache Read
¥0.04 / 1M tokens
Compare different providers across Zhinao API
111.72 tok/s
1.18 s
Uptime for deepseek/deepseek-v4-flash-vision-exp 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-flash-vision-exp",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);