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

DeepSeek V4 Flash Vision Exp

deepseek/deepseek-v4-flash-vision-exp
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731(opens in new tab) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total. It is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.
价格
输入$0.44/百万 tokens
Cached reads$0.028/百万 tokens
输出$1.32/百万 tokens

使用以下代码示例来集成我们的API:

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="<Your API Key>",
5    base_url="https://api.highwayapi.ai/openai"
6)
7
8response = client.chat.completions.create(
9    model="deepseek/deepseek-v4-flash-vision-exp",
10    messages=[
11        {"role": "system", "content": "You are a helpful assistant."},
12        {"role": "user", "content": "Hello, how are you?"}
13    ],
14    max_tokens=393216,
15    temperature=0.7
16)
17
18print(response.choices[0].message.content)

信息

提供商
量化
-

支持的功能

上下文长度
1M
最大输出
393.2K
serverless
支持
函数调用
支持
结构化输出
支持
推理
支持
Input Capabilities
text, image
Output Capabilities
text
联系我们