The Decoder 🧠 Models 👁 41 ⏱ 1 min read

Alibaba releases Qwen3.8-Flash-Next, targeting "ultimate cost efficiency"

Alibaba's Qwen team is previewing the Qwen4 architecture with Qwen3.8-Flash-Next, a mixture-of-experts model that activates just 6 out of 125 billion parameters per token. At one-ninth the training cost, it beats much larger competitors like DeepSeek-V4-Flash and Claude Opus 4.6 on coding and…

Annons
Annons
Alibaba's Qwen team is previewing the Qwen4 architecture with Qwen3.8-Flash-Next, a mixture-of-experts model that activates just 6 out of 125 billion parameters per token. At one-ninth the training cost, it beats much larger competitors like DeepSeek-V4-Flash and Claude Opus 4.6 on coding and office benchmarks, adding more pricing pressure on OpenAI and Anthropic. The article Alibaba releases Qwen3.8-Flash-Next, targeting "ultimate cost efficiency" appeared first on The Decoder.

Source: The Decoder — Published — Category: Models

🔗 Read full article on The Decoder →
🏷️ Topics: Claude

More from The Decoder today

OpenAI says a misaligned model deliberately destroyed its own environment hoping for a fresh start with better data 19h ago Microsoft's Decision-1 model enters the fast-growing AI decision model race 19h ago "How much beauty have we lost?" Mathematicians react with shock and disgust as OpenAI bulldozes their field 21h ago

More in Models

Latent Space12h ago

[Subscriber Exclusive] NYC Subscriber Meetups!
The Decoder19h ago

OpenAI says a misaligned model deliberately destroyed its own environment hoping for a fresh start with better data
The Decoder19h ago

Microsoft's Decision-1 model enters the fast-growing AI decision model race
Latent Space20h ago

Building AI for Reliable Execution: Lessons From Industrial Robotics
The Decoder21h ago

"How much beauty have we lost?" Mathematicians react with shock and disgust as OpenAI bulldozes their field
The Decoder24h ago

Few people pay for AI, but those who do spend big
Annons
Annons