DeepSeek
DeepSeek V4.1 Flash 1017
Open weights
- Intelligence
- 18.5
- Rank 277 of 768 measured models
- Output speed
- 166 t/s
- Rank 69 of 425 measured models
- Price/1M
- $0.525
- Rank 312 of 726 measured models
- Context window
- 1M
- Rank 90 of 1296 measured models
- Cost per task
- $0.425
- Rank 102 of 218 measured models
DeepSeek V4.1 Flash 1017 (Non-reasoning) scores 18.5 on the Artificial Analysis Intelligence Index, ranking 277th of 768 measured models. The closest models on this index are JT-35B-Flash (18.7), KAT-Coder-Pro V1 (18.6), and MiniMax-M2 (18.6). At $0.525 per million tokens (3:1 input/output blended price), it is priced close to MiniMax-M2 ($0.525). With an output speed of 166 t/s, it is faster than MiniMax-M2 (118 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- JT-35B-Flash
China Mobile · — · —
18.7+0.2——Compare - KAT-Coder-Pro V1
KwaiKAT · — · —
18.6+0.1——Compare - MiniMax-M2
MiniMax · $0.525 · 118 t/s
18.6+0.1$0.525118 t/sCompare - Qwen3.6 35B A3B
Alibaba · $0.844 · 128 t/s
18.2−0.3$0.844128 t/sCompare
