none · thinking
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / ALIBABA CLOUD
Alibaba Cloud flagship Qwen model for long-horizon coding, professional knowledge work, multimodal understanding and agentic workflows.
PRIMARY-SOURCE VERIFIED
Alibaba Cloud documents a 1,000,000-token context window. Input modalities: text + image + video. Output: text. Pricing status: Official paid API.
CAPABILITY CONTRACT
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
Input modalities come from the cited official model documentation.
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
$1.65 input · $0.206 cached · $4.95 output / MTok.
Only provider-published Standard paid token rates enter the SXF calculator. Partner hosting prices, negotiated rates and self-hosting costs are not substituted for a missing provider rate.
CAVEATS
SXF stores the Global list price; Alibaba Cloud publishes separate pricing for some regional scopes.
The official model page lists a 1,000,000-token context window and 131,072-token maximum output.
The current stable alias supports both non-thinking and thinking modes.
Knowledge cutoff remains unknown because the cited official documentation does not publish one.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for Qwen3.8 Max since 2026-10-06.
VERIFIED CHANGE HISTORY
Baseline verified: 1,000,000 context · 131,072 max output · $1.65 input / $4.95 output per MTok
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head 2ea333e862b9…