DeepSeek V3.1
Open weights
DeepSeek's August 2025 mid-generation update - a single hybrid model that switches between thinking and non-thinking modes.
- Publisher
- DeepSeek
- Family
- Deepseek V3
- Params
- 671B total / 37B active
- Context
- 128K
- Input
- Output
- License
- MIT
- Released
- 21 Aug 2025
Cite
Notes
Only stored in your browser.
Context
128K
Input
$0.57
/1M tok
Output
$1.68
/1M tok
Blended
$0.85
#339/ 461/1M · 3:1
Speed
0
#115/ 461tok/s
Price & speed via Artificial Analysis · ranked across tracked models
| Reasoning effort | Index | Price | Speed |
|---|---|---|---|
| Reasoning | 21.0 | $0.86 | 0 t/s |
| Non-reasoning | 21.4 | $0.85 | 0 t/s |
Intelligence Index per reasoning-effort setting, via Artificial Analysis
Reported on 14 evals across 9 domains - best 89.7% on AIME 2025: Problems from the American Invitational Mathematics Examination · #12 of 205