Moonshot AI
11 Canonical ModelsMoonshot AI foundation models, inference API endpoints, and pricing.
Models by Moonshot AI
Specifications, context windows, and pricing for Moonshot AI models
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
Kimi reasoning model for long-horizon research, planning, and tool use
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
Lower-latency Kimi Code variant for interactive edits and coding-agent loops
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
Thinking Kimi model for slower research passes, planning, and hard technical questions
September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding
Kimi model for long-context chat, coding, and agentic reasoning
Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents