Ling-3.0-flash (free)

Ling-3.0-flash is InclusionAI's production-oriented Mixture-of-Experts language model with 124B total parameters (~5.1B active per token) and a 262K-token context window. It targets agentic workflows including coding agents, tool use, document processing, and long multi-turn conversations where latency and token cost are critical. Source: supabase.