DeepSeekDeepSeek V4 Flash Vision (Reasoning, Max Effort)
- Released
- Aug 21, 2026
- Tracked since
- 2026-08-27
Intelligence index34.8Ranks 66 of 664 models with this metric
Coding index65Ranks 67 of 259 models with this metric
Agentic index47.5Ranks 25 of 156 models with this metric
Capability profile
5 axes vs. site averageDeepSeek V4 Flash Vision (Reasoning, Max Effort)
Site average
Pricing
per 1M tokens- Input
- $0.440
- Output
- $1.32
- Cache read
- $0.010
Performance
- Output throughput
- 220 tokens/sec
- Time to first token
- 890ms
- First answer token
- 9.99s
- End-to-end response
- 12.27s
History
5Intelligence index
51.5→34.8
Output
Unchanged across 62 days of records
Output throughput
119→220
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%