Models

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

MiMo Flash model for multimodal coding agents and long-context automation

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

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.

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

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

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

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