0

R1

Open weights

DeepSeek's open-weights reasoning model - the January 2025 release that triggered the "DeepSeek moment" in global AI markets.

Publisher
DeepSeek
Params
671B total / 37B active
Context
164K
Input
Output
License
MIT
Released
20 Jan 2025

Cite

Notes

Only stored in your browser.

Context
164K
Input
$1.68
/1M tok
Output
$4.70
/1M tok
Blended
$2.43
#349/ 414/1M · 3:1
Speed
0
#221/ 414tok/s

Price & speed via Artificial Analysis · ranked across tracked models

Reported on 21 evals across 10 domains - best 96.6% on MATH-500 · #20 of 178

Reported eval scores

21

Introduced in

paperDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning