Meta's efficient MoE model optimized for speed and cost. 16 experts deliver competitive quality at half the cost of Maverick, with the same 128K context length for versatile applications.
16 experts provide excellent quality with lower resource needs.
Same extended context as Maverick for long document processing.
Pay per token with auto-scaling
Cost-effective solution for high-throughput applications.
Fast response times for interactive applications.
Get excellent performance at half the cost of larger models.
Optimized for speed with smaller expert count.
Half the price of Maverick with competitive quality.
Reserved GPU for consistent performance
Quick content analysis at scale.
Efficient categorization of documents and messages.