Models

DeepSeek V4.1 Flash model for reasoning and agentic coding

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Open flagship GLM for long-horizon coding agents and million-token context work

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

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

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