ByteDance: Doubao-1.5-pro-32k API
A premium Pro-tier model leveraging a Sparse MoE architecture. It strikes an optimal balance between intelligence and speed, featuring a "Deep Thinking" mode for complex reasoning and high-fidelity multimodal understanding within a 32k window.
- Context window: 32,768 tokens
- Max output: 4,096 tokens
- Input: text, audio, image
- 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-pro-32k?
Doubao-1.5-pro-32k supports a context window of up to 32,768 tokens.
Does Doubao-1.5-pro-32k support function calling?
Yes. Doubao-1.5-pro-32k supports tool / function calling.
Does Doubao-1.5-pro-32k support reasoning?
Yes. Doubao-1.5-pro-32k is a reasoning-capable model.
What is the knowledge cutoff of Doubao-1.5-pro-32k?
The knowledge cutoff of Doubao-1.5-pro-32k is 2025-08-31.