Alibaba Prices Qwen3.8-Flash API At $0.16 Per Million Tokens, Cutting Inference Costs For 125B-Parameter Model
Covered by 1 source · 1 article
Alibaba's Qwen3.8-Flash-Next debuts as a 125B open-weight MoE previewing Qwen4 architecture, activating 6B params per token at $0.16/1M input tokens. The post Alibaba Prices Qwen3.8-Flash API At $0.16 Per Million Tokens, Cutting Inference C…
Covered by
