DeepSeek's reasoning-focused language model release.
Pricing
Official site · Jun 21, 2026, 1:09 PM
Input / 1M
$0.55
Output / 1M
$2.19
Cached input / 1M
$0.14
Official pricing page lists separate cache-hit and cache-miss input prices; inputPricePer1M records the cache-miss rate.
DeepSeek's official API pricing page lists DeepSeek-R1 as a text model billed per million tokens in USD, with separate cache-hit and cache-miss input rates.
Model Intelligence
Arena ranking
20
Benchmarkable
Yes
Model level
release
Intelligence Index
20.1
Math Index
76
MMLU Pro
0.85
GPQA
0.81
HLE
0.15
LiveCodeBench
0.77
SciCode
0.4
MATH-500
0.98
AIME
0.89
AIME 2025
0.76
IFBench
0.4
LCR
0.55
TerminalBench Hard
0.16
TAU2
0.37
Recent stories
0 linked stories
No linked stories yet.