Model Releases

Qwen3.8-Flash open-sourced as early preview of Qwen4 architecture

Original title:API is live on QwenCloud: https://www.qwencloud.com/models/qwen3.8-flash 🙌Let's build something!

AI summary

Qwen released Qwen3.8-Flash, a multimodal MoE model serving as an early preview of the Qwen4 architecture with open weights. The model has 125B total parameters but activates only 6B per token, with training cost just 1/9 that of Qwen3.7-Plus while outperforming it across the board. Production API pricing is $0.16 per 1M input tokens and $0.47 per 1M output tokens, with native 262K context extendable to 1M.

Key Takeaways

  • Qwen released Qwen3.
  • 8-Flash,a multimodal MoE model serving as an early preview of the Qwen4 architecture with open…
  • The model has 125B total parameters but activates only 6B per token,with training cost just 1/9…
  • 7-Plus while outperforming it across the board.
  • Production API pricing is $0.

Quick Facts

Published
Updated
Source
X:通义千问 / Qwen (@Alibaba_Qwen)
Category
Model Releases
AI score
84
Read the original Read the full article at the original source
Why it matters

训练成本降到前代的九分之一,同时编码和办公任务基准分数更高,对成本敏感的 API 调用场景提供了一个新的权衡参考点。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Qwen3.8-Flash open-sourced as early preview of Qwen4 architecture. August 26, 2026. https://new.nat6.net/en/news/cmta9ciqt07c1roj219h5liie/

View all →