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 |
|---|---|---|---|---|---|---|
| fp4 | 1.05M | ¥0.10 | ¥8.59 | ¥0.09 | 99.7% | |
O OpenInference | fp4 | 1.05M | ¥0.11 | ¥8.59 | ¥0.10 | 99.9% |
S Sail Research | fp4 | 1.05M | ¥0.13 | ¥2.01 | ¥0.09 | 98.4% |
S Sail Research | fp4 | 1.05M | ¥0.13 | ¥2.82 | ¥0.08 | 96.4% |
R Reka | — | 262K | ¥0.14 | ¥3.55 | ¥0.04 | 99.8% |
| fp8 | 1.02M | ¥0.30 | ¥0.89 | ¥0.01 | 99.7% | |
I Inceptron | fp4 | 1.05M | ¥0.34 | ¥4.36 | ¥0.18 | 99.8% |
| fp8 | 1.05M | ¥0.40 | ¥1.21 | ¥0.10 | 99.8% | |
| — | 1.05M | ¥0.80 | ¥1.60 | ¥0.16 | 99.7% | |
W Wafer (Fast) | — | 1.05M | ¥0.81 | ¥6.71 | ¥0.34 | 100.0% |
| fp8 | 1.05M | ¥0.87 | ¥1.75 | ¥0.19 | 100.0% | |
| fp8 | 1.05M | ¥0.87 | ¥1.75 | ¥0.19 | 100.0% | |
C CoreWeave | fp8 | 262K | ¥0.87 | ¥1.88 | ¥0.47 | 100.0% |
| — | 1.05M | ¥0.94 | ¥1.88 | ¥0.47 | 99.5% | |
| — | 1.05M | ¥0.94 | ¥1.88 | ¥0.20 | 99.6% | |
| fp8 | 1.05M | ¥0.94 | ¥1.88 | ¥0.34 | 99.7% | |
| bf16 | 1.05M | ¥0.95 | ¥2.69 | ¥0.24 | 98.1% | |
| — | 1.00M | ¥1.18 | ¥2.35 | ¥0.24 | 99.5% | |
M Mancer 2 | fp8 | 1.05M | ¥1.34 | ¥4.03 | - | 99.2% |
S SiliconFlow | fp8 | 1.05M | ¥1.48 | ¥4.43 | ¥0.19 | 99.4% |
G GMICloud限时 -35% | fp8 | 1.05M | ¥1.92 | ¥5.76 | ¥0.06 | 100.0% |
N NextBit | fp8 | 1.05M | ¥2.36 | ¥7.09 | ¥0.08 | 100.0% |
| — | 1.00M | ¥2.36 | ¥7.09 | ¥0.24 | 99.0% | |
| fp8 | 1.05M | ¥2.75 | ¥8.24 | ¥0.17 | 100.0% | |
P Phala | — | 1.05M | ¥2.95 | ¥8.86 | ¥0.19 | 99.8% |
| fp8 | 1.05M | ¥2.95 | ¥8.86 | ¥0.09 | 99.9% | |
| fp4 | 1.05M | ¥2.95 | ¥8.86 | ¥0.19 | 99.9% | |
| — | 1.05M | ¥2.95 | ¥8.86 | ¥0.09 | 100.0% |
¥0.10
输入/M
¥8.59
输出/M
¥0.09
缓存/M
99.7%
可用率
O
OpenInferencefp4¥0.11
输入/M
¥8.59
输出/M
¥0.10
缓存/M
99.9%
可用率
S
Sail Researchfp4¥0.13
输入/M
¥2.01
输出/M
¥0.09
缓存/M
98.4%
可用率
S
Sail Researchfp4¥0.13
输入/M
¥2.82
输出/M
¥0.08
缓存/M
96.4%
可用率
R
Reka¥0.14
输入/M
¥3.55
输出/M
¥0.04
缓存/M
99.8%
可用率
¥0.30
输入/M
¥0.89
输出/M
¥0.01
缓存/M
99.7%
可用率
I
Inceptronfp4¥0.34
输入/M
¥4.36
输出/M
¥0.18
缓存/M
99.8%
可用率
¥0.40
输入/M
¥1.21
输出/M
¥0.10
缓存/M
99.8%
可用率
¥0.80
输入/M
¥1.60
输出/M
¥0.16
缓存/M
99.7%
可用率
W
Wafer (Fast)¥0.81
输入/M
¥6.71
输出/M
¥0.34
缓存/M
100.0%
可用率
¥0.87
输入/M
¥1.75
输出/M
¥0.19
缓存/M
100.0%
可用率
¥0.87
输入/M
¥1.75
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
¥0.94
输入/M
¥1.88
输出/M
¥0.47
缓存/M
99.5%
可用率
¥0.94
输入/M
¥1.88
输出/M
¥0.20
缓存/M
99.6%
可用率
¥0.94
输入/M
¥1.88
输出/M
¥0.34
缓存/M
99.7%
可用率
¥0.95
输入/M
¥2.69
输出/M
¥0.24
缓存/M
98.1%
可用率
¥1.18
输入/M
¥2.35
输出/M
¥0.24
缓存/M
99.5%
可用率
M
Mancer 2fp8¥1.34
输入/M
¥4.03
输出/M
-
缓存/M
99.2%
可用率
S
SiliconFlowfp8¥1.48
输入/M
¥4.43
输出/M
¥0.19
缓存/M
99.4%
可用率
G
GMICloudfp8限时 -35%¥1.92
输入/M
¥5.76
输出/M
¥0.06
缓存/M
100.0%
可用率
N
NextBitfp8¥2.36
输入/M
¥7.09
输出/M
¥0.08
缓存/M
100.0%
可用率
¥2.36
输入/M
¥7.09
输出/M
¥0.24
缓存/M
99.0%
可用率
¥2.75
输入/M
¥8.24
输出/M
¥0.17
缓存/M
100.0%
可用率
P
Phala¥2.95
输入/M
¥8.86
输出/M
¥0.19
缓存/M
99.8%
可用率
¥2.95
输入/M
¥8.86
输出/M
¥0.09
缓存/M
99.9%
可用率
¥2.95
输入/M
¥8.86
输出/M
¥0.19
缓存/M
99.9%
可用率
¥2.95
输入/M
¥8.86
输出/M
¥0.09
缓存/M
100.0%
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