DeepSeek V4.1 Flash

Chat
deepseek/deepseek-v4.1-flash
对比试用 Playground开始使用

DeepSeek V4.1 Flash is DeepSeek's latest efficiency-optimized Mixture-of-Experts model with a 1M-token context window and up to 384K output tokens. It adds native multimodal vision understanding, supports thinking mode (on by default), tool calls, JSON output and prompt caching, and per DeepSeek surpasses V4 Pro on quality, cost and speed. Served upstream under the official model id deepseek-flash.

上下文窗口
1M
最大输出 Token
384K
发布日期
2026-09-10
能力
视觉函数调用推理提示缓存
可用供应商
DeepSeek
支持的协议
openaianthropic

供应商

DeepSeek
输入 Token
$0.3/M
输出 Token
$1.2/M
缓存读取
$0.006/M
接入协议
openai/v1/chat/completions/v1/responses
anthropic

代码示例

from openai import OpenAI


client = OpenAI(
    base_url="https://api.ofox.ai/v1",
    api_key="YOUR_OFOX_API_KEY",
)


response = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)


print(response.choices[0].message.content)

相关模型

更多 DeepSeek 模型

DeepSeek V4 Pro 0813
$1.32/M/$3.96/M
DeepSeek V4 Flash 0731
$0.44/M/$1.32/M
DeepSeek V4 Flash 0423
$0.44/M/$1.32/M

类似模型

OpenAI: GPT-6 Astra
$10/M/$50/M
Google: Gemini 3.8 Flash
$1.5/M/$7.5/M
Qwen: Qwen3.8 Max 0902
$2/M/$6/M

常见问题

DeepSeek V4.1 Flash 在 Ofox.ai 上的价格为输入 $0.3/M/百万 Token，输出 $1.2/M/百万 Token。按量计费，无月费。