Qwen3.8 Max
defaultAlibaba Cloud Model Studio's most capable Qwen (Qwen3.8, Aug 2026): 1M context, text, image and video input, thinking on by default and built-in web search (enable_search).
- Context window
- 1M tokens
- Max output
- 131K tokens
- Input / output
- text, image, video / text
- Latency
- slower (deliberate)
- Structured output
- yes
- Tool use / native search
- yes / yes
How to prompt it: Thinking is on by default (enable_thinking, with thinking_budget to cap it); turn it off for quick answers. For JSON use response_format json_schema with strict, or json_object with the word 'JSON' in the prompt (otherwise the API returns an error).
Verified on November 14, 2026 · official source