Models

Large coding-reasoning model for agentic software tasks and RL search

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

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

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

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

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

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

Large open Qwen multimodal MoE for visual agents and long technical tasks

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.

Large coding-reasoning model for agentic software tasks and RL search

Open multimodal Qwen MoE for local agents that need vision, audio, and code

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

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

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Open coding-reasoning model for repository tasks and self-improving agents