A 7B sparse Mixture-of-Experts (SMoE). Uses 12.9B active parameters out of 45B total.
Try NowGeneral text task at moderate cost
Multilingual content generation
Efficient inference at scale
32,768 tokens
32,768 tokens
$0.70 per 1M tokens
$0.70 per 1M tokens
$15 per 1K calls
$0.19 per 1K calls