Models

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

MiniMax multimodal model for long-context coding, perception, and agent planning

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Open MiniMax flagship for coding agents, office automation, and complex environments

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

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Newer StepFun flash model for faster agents, coding, and multimodal prompts

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

StepFun flash lane for quick multimodal reasoning and coding assistance

Qwen vision-language model for visual reasoning, documents, and agent tasks

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

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