/Models/MoonshotAI: Kimi Linear 48B A3B Instruct
Kimi

MoonshotAI: Kimi Linear 48B A3B Instruct

1049k context
Lowest Price
$0.70
per 1M tokens
Providers
1
Available
Context
1049k
tokens

Price Comparison

ProviderInput / OutputLatencyStatus
OpenRouterOpenRouterLowest
$0.70/$0.90
...
Verified

About This Model

Kimi Linear is a hybrid linear attention architecture that outperforms traditional full attention methods across various contexts, including short, long, and reinforcement learning (RL) scaling regimes. At its core is Kimi Delta Attention (KDA)—a refined version of Gated DeltaNet that introduces a m...

Quick Start