Compare Models
DeepSeek V4 Flash

Release Date: Apr 23, 2026

Developer DeepSeek 🇨🇳
Context Window 1M
Max Output Tokens 384k
Token Costs (in/out) $0.44/1.32
Weights Open
Input Modalities

Accuracy

66.72 %

Avg. Cost (In/Out)

$ 0.44 / $ 1.32

Latency

14 min 18 s

Vals Index
BenchmarksAccuracyRankings
CyberBench

0.0%

±6.11
14/22
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : DeepSeek
Temperature: 1
Top P: Default
Top K: Default
Max Output Tokens: 384,000
Reasoning Effort: high