ByteDance: Doubao-1.5-vision-pro-32k API
A flagship vision-language model leveraging a sparse MoE architecture (20B active params). It features native dynamic resolution and a "Thinking Mode" for complex visual reasoning, document parsing, and GUI automation, rivaling GPT-4o in visual IQ.
- Context window: 32,768 tokens
- Max output: 4,096 tokens
- Input: text, image, video
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-01-21
- Knowledge cutoff: 2025-08-31
Frequently Asked Questions
What is the context window of Doubao-1.5-vision-pro-32k?
Doubao-1.5-vision-pro-32k supports a context window of up to 32,768 tokens.
Does Doubao-1.5-vision-pro-32k support function calling?
Yes. Doubao-1.5-vision-pro-32k supports tool / function calling.
Does Doubao-1.5-vision-pro-32k support reasoning?
Yes. Doubao-1.5-vision-pro-32k is a reasoning-capable model.
What is the knowledge cutoff of Doubao-1.5-vision-pro-32k?
The knowledge cutoff of Doubao-1.5-vision-pro-32k is 2025-08-31.