DeepSeekDeepSeek V4 Flash 0731 (Reasoning, Max Effort)
- Released
- Jul 31, 2026
- Tracked since
- 2026-07-31
Intelligence index34.3Ranks 70 of 664 models with this metric
Coding index69.1Ranks 55 of 259 models with this metric
Agentic index41Ranks 42 of 156 models with this metric
Capability profile
5 axes vs. site averageDeepSeek V4 Flash 0731 (Reasoning, Max Effort)
Site average
Pricing
per 1M tokens- Input
- $0.440
- Output
- $1.32
- Cache read
- $0.010
Performance
- Output throughput
- 225 tokens/sec
- Time to first token
- 1.02s
- First answer token
- 9.89s
- End-to-end response
- 12.10s
History
9Intelligence index
49.9→34.3
Output
$0.280→$1.32
Output throughput
104→225
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.8-Flash-Next
AlibabaIntelligence 39.8$0.470−64% - GLM 5.3 Flash
Z AIIntelligence 41.8$0.500−62% - GPT-6 Luna (max)
OpenAIIntelligence 37.3$0.500−62% - GPT-6 Luna (xhigh)OpenAIIntelligence 33.9$0.500−62%
- MiMo-V2.6-Pro
XiaomiIntelligence 46.3$0.870−34%