MiMo-V2.5-Pro is an open-source Mixture-of-Experts (MoE) language model with 1.02T total parameters and 42B active parameters. It utilizes the hybrid attention architecture and 3-layers Multi-Token Prediction (MTP) introduced in MiMo-V2-Flash, with up to 1M tokens context length.
MiMo-V2.5-Pro is our most capable model to date, designed for the most demanding agentic, complex software engineering, and long-horizon tasks. It sustains complex trajectories spanning thousands of tool calls with strong instruction following and coherence over a 1M-token context window. Key features include:
- Hybrid Attention Architecture: Interleaves Sliding Window Attention (SWA) and Global Attention (GA) with a 6:1 ratio and 128 sliding window. This reduces KV-cache storage by nearly 7x while maintaining long-context performance via learnable attention sink bias. - Multi-Toke…
Источник каталога: https://models.dev/api.json. Получено: 05.11.2026 16:25 UTC. Цены и лимиты — данные источника; перед использованием проверяйте условия поставщика.