Models

Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding

Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows

Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window

Open MoE flagship with million-token context for coding and long agent runs

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Agentic coding model from Poolside in the XS size class for local deployment

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads