Changelog
Qwen3.8 27B now on a faster free lane
The same Qwen3.8 27B weights are now served from Groq under a new id, qwen3.8-27b-1:free, with 1,000 requests a day. The original qwen3.8-27b:free stays.
2 min read
Blog
Qwen4 Max Preview:free — API Pricing, Providers & Specs
Qwen4 Max Preview from $3/month on Alibaba’s Token Plan: verified specs, a factual comparison vs Gemini 4 Carbon, Argon and Claude, free routes and code.
21 min read
Blog
Use Qwen4 Max Preview in Claude Code, Cursor, Codex and Cline
Qwen4 Max Preview speaks OpenAI and Anthropic protocols, so Claude Code, Cursor, Codex, Cline and Qwen Code can all point at it. Base URL, key and model id.
7 min read
Blog
Qwen4 Max Preview Context Window: the 1M-Token Window and 390K Output, and How to Use It
Alibaba docs list a 1M token context with about 390K output on Qwen4 Max Preview. What that means for long docs, codebases and agents, plus chunking patterns.
8 min read
Blog
The Qwen4 Family: Max, Plus, Flash and the 27B You Can Run Yourself
Qwen4 Max Preview is the only size shipped, but the slide showed four: Max, Plus, Flash and a 27B you can run yourself. Cloud vs local, and which to pick.
8 min read
Blog
Qwen4 Max Preview Has No Benchmarks Yet — Here Is What Is Real and What Is a Leak
Qwen4 Max Preview shipped with zero official scores. We traced the viral numbers to their sources; most are not what they claim.
8 min read
Blog
Is Qoduck Qwen4 Max? The Stealth Model Clues, the Koduck Claim and What Alibaba Has Actually Confirmed
Qoder ran a free stealth model called Qoduck during Qwen4 launch week, and a Chinese site claims Koduck was an early checkpoint. Every clue, confirmed and not.
8 min read
Blog
Qwen4 Max Preview Speed Test: the 20-Minute Pelican and What Early Numbers Really Say
Qwen4 Max Preview is hours old, so early speed reports are thin: a 20-minute pelican at roughly 20 tokens a second. What the numbers do and do not tell you.
9 min read