Alibaba: qvq-max API
Alibaba's flagship visual reasoning model. Built on the Qwen2.5-Max backbone, it integrates "Deep Thinking" to solve complex multimodal tasks, including geometric proofs, architectural analysis, and multi-step video reasoning, rivaling GPT-4o-vision and Gemini 3 Pro.
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input: text, image, video
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- Released: 2025-03-25
- Knowledge cutoff: 2025-08-31
Frequently Asked Questions
What is the context window of qvq-max?
qvq-max supports a context window of up to 131,072 tokens.
Does qvq-max support function calling?
Yes. qvq-max supports tool / function calling.
Does qvq-max support reasoning?
Yes. qvq-max is a reasoning-capable model.
What is the knowledge cutoff of qvq-max?
The knowledge cutoff of qvq-max is 2025-08-31.