Doubao-1.5-Pro
Sparse MoE flagship with 20B active params rivaling 140B dense models.
About
Doubao-1.5-Pro is ByteDance's flagship general-purpose language model, released in January 2025. It uses a sparse mixture-of-experts architecture with 20 billion activated parameters per token, which ByteDance reports delivers performance comparable to a 140 billion parameter dense model at a fraction of the compute cost.
The model ships in 32K and 256K context configurations with a deep thinking reasoning mode, and benchmarks cited by ByteDance show it ahead of GPT-4o and Claude 3.5 Sonnet on knowledge, coding, and Chinese language tasks. It is closed weights, available through the Volcano Engine API and the Doubao app, which had over 150 million monthly users by late 2025.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 107; Trending score 75/100 from researcher assessment.