Alibaba: Qwen3.6 Flash API
The Flash model of the Qwen3.6 native vision-language series, a clear step up from 3.5-Flash, focused on agentic coding, math and code reasoning, with markedly better spatial intelligence, object localization and detection.
- Context window: 1,000,000 tokens
- Max output: 65,536 tokens
- Input: text, image, video
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2026-04-16
Frequently Asked Questions
What is the context window of Qwen3.6 Flash?
Qwen3.6 Flash supports a context window of up to 1,000,000 tokens.
Does Qwen3.6 Flash support function calling?
Yes. Qwen3.6 Flash supports tool / function calling.
Does Qwen3.6 Flash support reasoning?
Yes. Qwen3.6 Flash is a reasoning-capable model.