1T param MoE, 32B active - 200-300 sequential tool calls autonomously, $4.6M training cost
Context Window
256,000
tokens
Max Output
8,192
tokens
Input Pricing
$0.60
per million tokens
Output Pricing
$2.50
per million tokens
Agentic
200-300 sequential autonomous tool calls
Long Context
256K token context window
No benchmark scores available