
No ratings yet
Be the first to review this model
AI21's compact SSM-Transformer hybrid model delivering 2.5x faster inference on long contexts than competitors. Features a 256K context window with function calling and structured JSON output for enterprise use. Outperforms larger models like Mixtral 8x22B while being significantly more efficient.
Released
August 22, 2024
Parameters
52B (12B active)
Context
256K
Pricing
Open Source
Last updated: March 15, 2026
Benchmark scores may vary based on evaluation methodology and conditions.