All AI models · LLM benchmarks · Methodology

Moonshot AI

Kimi K2 Thinking

Kimi reasoning model for long-horizon research, planning, and tool use

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$0.47 per 1M tokens
Cheapest paid output
$2 per 1M tokens
Open weights
yes
Providers
23

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, open weights, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default33.5not measured94.7not measured

Observed price history

  • 2026-08-24: $0.47 input / $2 output per 1M tokens

API providers

  • Vercel AI Gateway — model id moonshotai/kimi-k2-thinking; $0.47 input / $2 output per 1M tokens; provider documentation
  • Helicone — model id kimi-k2-thinking; $0.48 input / $2 output per 1M tokens; provider documentation
  • IO.NET — model id moonshotai/Kimi-K2-Thinking; $0.55 input / $2.25 output per 1M tokens; provider documentation
  • 302.AI — model id kimi-k2-thinking; $0.575 input / $2.3 output per 1M tokens; provider documentation
  • OpenCode Zen — model id kimi-k2-thinking; $0.4 input / $2.5 output per 1M tokens; provider documentation
  • Amazon Bedrock — model id moonshot.kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Charm Hyper — model id kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Eden AI — model id amazon/moonshot.kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Hugging Face — model id moonshotai/Kimi-K2-Thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Kilo Gateway — model id moonshotai/kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • LLM Gateway (Vertex AI (OpenAI-compatible)) — model id vertex-openai/kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Merge Gateway — model id moonshotai/kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Moonshot AI — model id kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Moonshot AI (China) — model id kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • NanoGPT — model id moonshotai/kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • NovitaAI — model id moonshotai/kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • OpenRouter — model id moonshotai/kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Vertex — model id moonshotai/kimi-k2-thinking-maas; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • ZenMux — model id moonshotai/kimi-k2-thinking; $0.6 input / $2.5 output per 1M tokens; provider documentation
  • Meganova — model id moonshotai/Kimi-K2-Thinking; $0.6 input / $2.6 output per 1M tokens; provider documentation
  • Poe — model id novita/kimi-k2-thinking; not published input / not published output per 1M tokens; provider documentation
  • Qiniu — model id moonshotai/kimi-k2-thinking; not published input / not published output per 1M tokens; provider documentation