ByteDance: Doubao-1.5-pro-256k API
An upgraded flagship model utilizing a sparse MoE architecture with 20B active parameters (delivering 140B dense performance). Supporting a 256k context window and a 12k output limit, it features a "Deep Thinking" mode for advanced reasoning and multimodal understanding, optimized for large-scale enterprise data management.
- Context window: 256,000 tokens
- Max output: 12,288 tokens
- Input: text, audio, 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-pro-256k?
Doubao-1.5-pro-256k supports a context window of up to 256,000 tokens.
Does Doubao-1.5-pro-256k support function calling?
Yes. Doubao-1.5-pro-256k supports tool / function calling.
Does Doubao-1.5-pro-256k support reasoning?
Yes. Doubao-1.5-pro-256k is a reasoning-capable model.
What is the knowledge cutoff of Doubao-1.5-pro-256k?
The knowledge cutoff of Doubao-1.5-pro-256k is 2025-08-31.