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.

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.