R1
DeepSeek's open-weights reasoning model - the January 2025 release that triggered the "DeepSeek moment" in global AI markets.
- Publisher
- DeepSeek
- Family
- Deepseek R
- Params
- 671B total / 37B active
- Context
- 64K
- Input
- Output
- License
- mit
- Released
- 20 Jan 2025
Cite
Notes
Only stored in your browser.
Attribution
- Benchmark scores
- AiderAAVaultarena-hard-autoLiveBenchOpenRewardAfterQueryVals AIEQ-Bench
Context
64K
Weights
Open
downloadable
Input
$1.35
/1M tok
Output
$3
/1M tok
Price & speed via Artificial Analysis · ranked across tracked models
| Reasoning effort | Index | Price | Speed |
|---|---|---|---|
| jan-25 | 11.4 | $2.50 | 0 t/s |
| may-25 | 13.1 | $1.76 | 0 t/s |
Intelligence Index per reasoning-effort setting, via Artificial Analysis
Reported on 23 evals across 11 domains - best 96.6% on MATH-500 · #27 of 190
Reported eval scores
23IFBench39
MMLU-Pro84.4
LiveBench66.8
MATH-50096.6
LiveCodeBench61.7
AIME202479.8
GPQA Diamond70.8
SciCode35.7
TaxEval v272.3
CorpFin v254.1