All AI models · LLM benchmarks · Methodology

Moonshot AI

Kimi K2.5 Thinking

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

Model facts

Context window
256K tokens
Maximum output
66K tokens
Cheapest paid input
$0.3 per 1M tokens
Cheapest paid output
$1.9 per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

reasoning, tool calling, attachments, open weights, text, image, pdf.

Observed price history

  • 2026-08-24: $0.3 input / $1.9 output per 1M tokens

API providers

  • NanoGPT — model id moonshotai/kimi-k2.5:thinking; $0.3 input / $1.9 output per 1M tokens; provider documentation
  • Arena — model id kimi-k2.5; not published input / not published output per 1M tokens; provider documentation