DeepSeek-R1
Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
A language reasoning model release from DeepSeek, released with reinforcement-learning training and open model weights.
Pricing
Model profile · Current snapshot
Input / 1M
$1.85
Output / 1M
$2.75
Blended / 1M
$2.08
Output TPS
0
TTFT (s)
0
Model Intelligence
Arena ranking
13
Benchmarkable
Yes
Model level
release
MMLU Pro
0.85
GPQA
0.81
HLE
0.16
LiveCodeBench
0.77
MATH-500
0.98
AIME
0.89
AIME 2025
0.76
IFBench
0.4
LCR
0.56
TerminalBench Hard
0.16
TAU2
0.37
Recent stories
0 linked stories
No linked stories yet.