Skip to content

DeepSeek V3.1

by DeepSeekRank #151Score 71.8

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

性能概览

评分
71.8
排名
#151
24小时变化
+1
7天变化
-45
状态
stable
置信度
high

信号评分

信号标准化权重贡献新鲜度
Capabilities
capability
66.720%13.32026-08-08T13:39:42.656Z
Benchmarks
benchmark
69.130%20.72026-08-08T13:39:42.656Z
Pricing
pricing_tier
99.115%14.92026-08-08T13:39:42.656Z
Context Window
context_window
82.810%8.32026-08-08T13:39:42.656Z
Recency
recency
68.715%10.32026-08-08T13:39:42.656Z
Output Capacity
output_capacity
75.010%7.52026-08-08T13:39:42.656Z

主要驱动因素

positive
Benchmarks
positive
Pricing
$0.95/M output tokens
$0.95
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Recency
Released over 1 year ago
12mo ago

功能

功能支持
视觉
推理
JSON模式
流式输出
函数调用
网页搜索

价格

输入/百万令牌
$0.25
输出/百万令牌
$0.95
上下文窗口
164K
最大输出
33K

相关模型

相关

DeepSeek V3.1 Tracker - Performance History | LM Market Cap