Yi: yi-vision-v2 API

01.AI's next-generation flagship multimodal model. Compared to its predecessor, v2 significantly enhances visual detail capture (e.g., small OCR text) and excels in complex chart analysis, multi-image logical correlation, and visual reasoning. It supports high-resolution inputs and provides precise comprehension of visual information in Chinese contexts, serving as a core brain for automated document processing and vision agents.

Frequently Asked Questions

What is the context window of yi-vision-v2?

yi-vision-v2 supports a context window of up to 131,072 tokens.

Does yi-vision-v2 support function calling?

Yes. yi-vision-v2 supports tool / function calling.

Does yi-vision-v2 support reasoning?

Yes. yi-vision-v2 is a reasoning-capable model.

What is the knowledge cutoff of yi-vision-v2?

The knowledge cutoff of yi-vision-v2 is 2025-05-31.