Alibaba: qvq-plus API
A high-performance visual reasoning model that balances speed and logic. Leveraging the Qwen3-VL architecture, it supports "Thinking Mode" for complex OCR and diagram analysis with a large context window, optimized for high-throughput enterprise multimodal agents.
- Context window: 262,144 tokens
- Max output: 8,192 tokens
- Input: text, image, video
- Output: text
- Released: 2025-09-10
- Knowledge cutoff: 2025-08-31
Frequently Asked Questions
What is the context window of qvq-plus?
qvq-plus supports a context window of up to 262,144 tokens.
What is the knowledge cutoff of qvq-plus?
The knowledge cutoff of qvq-plus is 2025-08-31.