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.
- Context window: 131,072 tokens
- Max output: 8,192 tokens
- Input: text, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-08-14
- Knowledge cutoff: 2025-05-31
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.