Qwen3.8-Max Just Went GA: A Developer's Guide to Alibaba's 2.4T Model
SMRTR summary
Alibaba's Qwen3.8-Max is a 2.4-trillion-parameter MoE model with 1M-token context, multimodal input, and OpenAI-compatible API, priced at $2/$6 per million tokens. With ~95B active parameters per token, it's cheaper than competitors like Kimi K3. Caching cuts input costs 8x, so prefix stability is critical. Open weights arrive the week of August 10.
SMRTR provides this summary for quick context. The original article belongs to Dev.to.
Read the original article