DeepSeek
DeepSeek V4.1 Flash 1017
ReasoningOpen weights
- Intelligence
- 28.6
- Rank 132 of 768 measured models
- Output speed
- 160 t/s
- Rank 83 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
- $0.456
- Rank 104 of 218 measured models
DeepSeek V4.1 Flash 1017 (High) scores 28.6 on the Artificial Analysis Intelligence Index, ranking 132nd of 768 measured models. The closest models on this index are DeepSeek V4.1 Flash (28.6), MiMo-V2-Pro (28.6), and GPT-5.2 Codex (Xhigh) (28.5). At $0.525 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.2 Codex (Xhigh) ($4.81), priced close to DeepSeek V4.1 Flash ($0.525). With an output speed of 160 t/s, it is faster than GPT-5.2 Codex (Xhigh) (104 t/s), slower than DeepSeek V4.1 Flash (193 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek V4.1 Flash
DeepSeek · $0.525 · 193 t/s
28.6$0.525193 t/sCompare - MiMo-V2-Pro
Xiaomi · — · —
28.6——Compare - GPT-5.2 Codex (Xhigh)
OpenAI · $4.81 · 104 t/s
28.5−0.1$4.81104 t/sCompare - Step 5 Preview
StepFun · $1.43 · 139 t/s
28.5−0.1$1.43139 t/sCompare
