DeepSeekDeepSeek V4 Pro 0424 (Reasoning, Max Effort)
- Released
- Apr 24, 2026
- Tracked since
- 2026-07-23
Intelligence index30.4Ranks 95 of 664 models with this metric
Coding index59.4Ranks 81 of 259 models with this metric
Agentic index26.3Ranks 71 of 156 models with this metric
Capability profile
5 axes vs. site averageDeepSeek V4 Pro 0424 (Reasoning, Max Effort)
Site average
Pricing
per 1M tokens- Input
- $0.430
- Output
- $0.870
- Cache read
- $0
Performance
- Output throughput
- 83 tokens/sec
- Time to first token
- 1.67s
- First answer token
- 54.36s
- End-to-end response
- 60.38s
History
6Intelligence index
44.3→30.4
Output
Unchanged across 62 days of records
Output throughput
62→83
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.8-Flash-Next
AlibabaIntelligence 39.8$0.470−46% - GLM 5.3 Flash
Z AIIntelligence 41.8$0.500−43% - GPT-6 Luna (max)
OpenAIIntelligence 37.3$0.500−43% - GPT-6 Luna (xhigh)OpenAIIntelligence 33.9$0.500−43%
- GPT-6 Luna (high)OpenAIIntelligence 32.1$0.500−43%