DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-exp

DeepSeek-V4-Flash-Vision-Exp 是 DeepSeek 推出的实验性多模态模型,在 V4-Flash 基础上加入原生视觉理解能力,并保留 100 万 token 上下文。单次请求中文本与图片可自由穿插,适用于文档与图表解析、界面理解,以及依赖视觉的 Agent 工作流。纯文本能力(Agent、推理、世界知识)与 V4-Flash 正式版持平;在需要视觉理解的 Agent 基准上,相比纯文本模型有大幅提升。

Model price

Input /Mt Output /Mt
UncachedCache read
¥3/Mt¥1/Mt¥9/Mt

Sample Code

Copy
1base_url="https://api.ppio.com/openai"
2api_key="<YOUR_API_KEY>"
3
4curl "$base_url/v1/chat/completions" \
5  -H "Content-Type: application/json" \
6  -H "Authorization: Bearer $api_key" \
7  -d @- << 'EOF'
8{
9    "model": "deepseek/deepseek-v4-flash-vision-exp",
10    "messages": [
11        
12        {
13            "role": "user",
14            "content": "Hi there!"
15        }
16    ],
17    "response_format": { "type": "text" }
18}
19EOF
20  

Model Information

Context window:

1M

Maximum output tokens:

393.2K

Modality:

Input:
TextImage
Output:
Text

Supported features

Function CallingSupported
Structured OutputSupported
reasoningSupported

API Integration Guide

Base URL:

https://api.ppio.com/openai

Messages protocol Base URL:

https://api.ppio.com/anthropic

API Endpoints:

/v1/chat/completions

Model ID:

deepseek/deepseek-v4-flash-vision-exp

Usage tierRPMTPM
T13050000000
T210050000000
T3100050000000
T4300050000000
T5600050000000
With more cost-effective products and services
Help you unleash boundless innovation and lead the new era of intelligence
Inquire now