Alibaba: Qwen3.7 Flash API
The Flash model of the Qwen3.7 native vision-language series, with across-the-board gains over 3.6-Flash in multimodal understanding and agent execution, stronger recognition, real-world perception and spatial intelligence, and better multimodal agent and coding performance.
- Context window: 1,000,000 tokens
- Max output: 131,072 tokens
- Input: text, image, video
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2026-07-21
Frequently Asked Questions
What is the context window of Qwen3.7 Flash?
Qwen3.7 Flash supports a context window of up to 1,000,000 tokens.
Does Qwen3.7 Flash support function calling?
Yes. Qwen3.7 Flash supports tool / function calling.
Does Qwen3.7 Flash support reasoning?
Yes. Qwen3.7 Flash is a reasoning-capable model.