- Intelligence
- 45.1
- Rank 37 of 749 measured models
- Output speed
- 227 t/s
- Rank 38 of 410 measured models
- Price/1M
- $0.525
- Rank 289 of 670 measured models
- Context window
- 1M
- Rank 86 of 1216 measured models
- Cost per task
- $0.262
- Rank 82 of 198 measured models
DeepSeek V4.1 Flash 1017 (Max) scores 45.1 on the Artificial Analysis Intelligence Index, ranking 37th of 749 measured models. The closest models on this index are Qwen3.8 Max (0902) (45.4), GLM-5.3 (44.8), and Grok 4.6 (44.3). At $0.525 per million tokens (3:1 input/output blended price), it is cheaper than Qwen3.8 Max (0902) ($3), GLM-5.3 ($2.15), and Grok 4.6 ($3). With an output speed of 227 t/s, it is faster than Qwen3.8 Max (0902) (37.8 t/s), GLM-5.3 (95.4 t/s), and Grok 4.6 (64.6 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- MiMo-V2.6-Pro
Xiaomi · $0.544 · 50.8 t/s
46.3+1.2$0.54450.8 t/sCompare - Qwen3.8 Max (0902)
Alibaba · $3 · 37.8 t/s
45.4+0.3$337.8 t/sCompare - GLM-5.3
Z.AI · $2.15 · 95.4 t/s
44.8−0.3$2.1595.4 t/sCompare - Grok 4.6
SpaceXSI · $3 · 64.6 t/s
44.3−0.8$364.6 t/sCompare
