Press Space to continue
Ling-3.0-flash MoE Model Available for Token-Efficient Inference
Press Space to continue
Ling-3.0-flash is live on OpenRouter via @novita_labs. A 124B-parameter MoE model with ~5.1B active per token, built for token-efficient, production-scale agentic inference. Free through August 3. Try it: https://openrouter.ai/inclusionai/ling-3…
Ling-3.0-flash (free) - API Pricing & Providers