DeepSeek V4 Flash
DeepSeek V4 Flash 0731 是 DeepSeek 推出的稀疏混合专家(MoE)模型,总参数 2840 亿,激活参数 130 亿。这一重训练修订版适用于编程、推理与 Agent 工作流。
模态
参数量 (MoE)
284B总
激活 13B / token
上下文
1.05Mtokens
最大输出 944K tokens
排名与分数走势
Deepseek V4 FlashDeepseek V4 Flash High (Preview)
排名
Elo 评分
能力
工具调用 (Tools)
结构化输出
并行工具调用
视觉输入
音频输入
多服务商价格对比数据来自 OpenRouter
| 服务商 | 量化精度 | 上下文 | 输入/M | 输出/M | 缓存读取/M | 近1天可用率 |
|---|---|---|---|---|---|---|
R Reka | — | 262K | ¥0.14 | ¥3.54 | ¥0.04 | 100.0% |
| fp8 | 1.05M | ¥0.40 | ¥1.20 | ¥0.01 | 99.7% | |
| fp8 | 1.05M | ¥0.40 | ¥1.21 | ¥0.10 | 100.0% | |
| fp4 | 1.05M | ¥0.47 | ¥0.94 | ¥0.09 | 100.0% | |
O OpenInference | fp4 | 1.05M | ¥0.47 | ¥0.94 | ¥0.09 | 99.5% |
| fp8 | 1.02M | ¥0.59 | ¥1.77 | ¥0.02 | 100.0% | |
S Sail Research | fp4 | 1.05M | ¥0.67 | ¥2.01 | ¥0.20 | 100.0% |
S Sail Research | fp4 | 1.05M | ¥0.67 | ¥2.01 | ¥0.20 | 100.0% |
| — | 1.05M | ¥0.80 | ¥1.59 | ¥0.16 | 100.0% | |
W Wafer | nvfp4 | 1.05M | ¥0.87 | ¥1.54 | ¥0.84 | 100.0% |
| fp8 | 1.05M | ¥0.87 | ¥1.74 | ¥0.19 | 92.8% | |
| fp32 | 1.05M | ¥0.87 | ¥1.74 | ¥0.19 | 93.2% | |
| — | 1.00M | ¥0.87 | ¥1.74 | ¥0.19 | 100.0% | |
C CoreWeave | fp8 | 262K | ¥0.87 | ¥1.88 | ¥0.47 | 100.0% |
I Inceptron | fp4 | 1.05M | ¥0.87 | ¥3.12 | ¥0.18 | 99.9% |
| — | 1.05M | ¥0.94 | ¥1.88 | ¥0.47 | 99.9% | |
| — | 1.05M | ¥0.94 | ¥1.88 | ¥0.20 | 99.1% | |
| fp8 | 1.05M | ¥0.94 | ¥1.88 | ¥0.33 | 100.0% | |
M Mancer 2 | fp8 | 1.05M | ¥1.34 | ¥4.02 | - | 99.9% |
S SiliconFlow | fp8 | 1.05M | ¥1.47 | ¥4.42 | ¥0.19 | 100.0% |
G GMICloud限时 -35% | fp8 | 1.05M | ¥1.92 | ¥5.75 | ¥0.06 | 100.0% |
| — | 1.00M | ¥2.36 | ¥7.07 | ¥0.24 | 99.1% | |
| — | 1.00M | ¥2.51 | ¥7.52 | ¥0.25 | 100.0% | |
| fp8 | 1.05M | ¥2.74 | ¥8.22 | ¥0.17 | 100.0% | |
P Phala | — | 1.05M | ¥2.95 | ¥8.84 | ¥0.19 | 100.0% |
| fp4 | 1.05M | ¥2.95 | ¥8.84 | ¥0.19 | 99.9% | |
| — | 1.05M | ¥2.95 | ¥8.84 | ¥0.09 | 99.9% |
R
Reka¥0.14
输入/M
¥3.54
输出/M
¥0.04
缓存/M
100.0%
可用率
¥0.40
输入/M
¥1.20
输出/M
¥0.01
缓存/M
99.7%
可用率
¥0.40
输入/M
¥1.21
输出/M
¥0.10
缓存/M
100.0%
可用率
¥0.47
输入/M
¥0.94
输出/M
¥0.09
缓存/M
100.0%
可用率
O
OpenInferencefp4¥0.47
输入/M
¥0.94
输出/M
¥0.09
缓存/M
99.5%
可用率
¥0.59
输入/M
¥1.77
输出/M
¥0.02
缓存/M
100.0%
可用率
S
Sail Researchfp4¥0.67
输入/M
¥2.01
输出/M
¥0.20
缓存/M
100.0%
可用率
S
Sail Researchfp4¥0.67
输入/M
¥2.01
输出/M
¥0.20
缓存/M
100.0%
可用率
¥0.80
输入/M
¥1.59
输出/M
¥0.16
缓存/M
100.0%
可用率
W
Wafernvfp4¥0.87
输入/M
¥1.54
输出/M
¥0.84
缓存/M
100.0%
可用率
¥0.87
输入/M
¥1.74
输出/M
¥0.19
缓存/M
92.8%
可用率
¥0.87
输入/M
¥1.74
输出/M
¥0.19
缓存/M
93.2%
可用率
¥0.87
输入/M
¥1.74
输出/M
¥0.19
缓存/M
100.0%
可用率
C
CoreWeavefp8¥0.87
输入/M
¥1.88
输出/M
¥0.47
缓存/M
100.0%
可用率
I
Inceptronfp4¥0.87
输入/M
¥3.12
输出/M
¥0.18
缓存/M
99.9%
可用率
¥0.94
输入/M
¥1.88
输出/M
¥0.47
缓存/M
99.9%
可用率
¥0.94
输入/M
¥1.88
输出/M
¥0.20
缓存/M
99.1%
可用率
¥0.94
输入/M
¥1.88
输出/M
¥0.33
缓存/M
100.0%
可用率
M
Mancer 2fp8¥1.34
输入/M
¥4.02
输出/M
-
缓存/M
99.9%
可用率
S
SiliconFlowfp8¥1.47
输入/M
¥4.42
输出/M
¥0.19
缓存/M
100.0%
可用率
G
GMICloudfp8限时 -35%¥1.92
输入/M
¥5.75
输出/M
¥0.06
缓存/M
100.0%
可用率
¥2.36
输入/M
¥7.07
输出/M
¥0.24
缓存/M
99.1%
可用率
¥2.51
输入/M
¥7.52
输出/M
¥0.25
缓存/M
100.0%
可用率
¥2.74
输入/M
¥8.22
输出/M
¥0.17
缓存/M
100.0%
可用率
P
Phala¥2.95
输入/M
¥8.84
输出/M
¥0.19
缓存/M
100.0%
可用率
¥2.95
输入/M
¥8.84
输出/M
¥0.19
缓存/M
99.9%
可用率
¥2.95
输入/M
¥8.84
输出/M
¥0.09
缓存/M
99.9%
可用率
📊 Artificial Analysis 综合指数
34.3
智能指数
69.1
编程指数
41
Agent 指数