DeepSeekactive
DeepSeek R1
Released at: January 20, 2025
API StatusAvailable for integration
Context Window163,840 tokens
Input Price / MTok$0.70
Output Price / MTok$2.50
Model Overview
A premier reasoning model employing large-scale reinforcement learning. Displays specialized math, coding, and logical validation capabilities comparable to OpenAI's o1.
Vetted Benchmarks
mmluScore: 90.8% (Ranked top 34%)
humanevalScore: 92.8% (Ranked top 40%)
mathScore: 93.1% (Ranked top 16%)
gpqaScore: 71.5% (Ranked top 39%)
mt_benchScore: 9.3% (Ranked top 45%)
hellaswagScore: 94% (Ranked top 61%)
Input Price TrendLast 90 Days
Output Price TrendLast 90 Days
How does this model compare?
Evaluate benchmark standing and performance rankings vs all other tracked models.