Ling 3.0 Flash
InclusionAI · text → text
ling-3.0-flash is Inclusionai's 124B Mixture-of-Experts (MoE) text model, designed for production-scale agentic inference and token-efficient text generation. Activating approximately 5.1B parameters per token, it offers an extensive 262,144-token context window alongside cost-effective pricing at $0.06 per 1M input, $0.18 per 1M output, and $0.01 per 1M cache tokens.
Input$0.06 /M
Output$0.18 /M
Cache read$0.012 /M