Qwen4 Spotted in Alibaba's Own Code: 1M-Token Default Context and a qwen4-omni-120b-think Variant

mark_k · x · 2026-10-31

Concrete integration clues for Qwen4 have surfaced in Alibaba's official qwen-code repo:

• Merged PR #15762 extends the context-window detector's 1M rule to the whole qwen4 generation, making 1M tokens the default context window (down from the 256K fallback, where auto-compaction fired at 22% of the real window).
• Test fixtures reference qwen4-omni-120b-think, an ID already in use as a session model, suggesting a multimodal reasoning variant is being prepared.
• Other IDs listed: qwen4, qwen4-max, qwen4-plus, qwen4-coder-plus, qwen4.5-max and more, all previously resolving to 262,144.

Caveats: the 1M figure is a client-side default, not a published spec, and no live Qwen4 endpoint was tested — but a release may be approaching.

Original post →

More from Models

• 5 cheap open models vote vs Opus: 89.6% accuracy at 1/10th the cost — PomegranateAble4339 · 2026-10-31
• Gemini 4 Carbon reportedly scores 53 FCI on FrontierCS 2, big jump from Argon in weeks — clmt · 2026-10-31
• Gemini 3.5 Pro reportedly delayed into oblivion while rivals took share, says dev — tarantulae · 2026-10-31
• Dev suspects longer training degraded Qwen backbone multilingual abilities, plans more multilingual data — antoine_chaffin · 2026-10-31
• LiquidAI's LFM3-VL d1-2B edge vision-language model trends on Hugging Face — LiquidAI · 2026-10-31
• OpenAI's new API credits make ChatGPT Pro tiers a no-brainer for API users — Quiet-Recording-9269 · 2026-10-31

Models channel →