All AI models · LLM benchmarks · Methodology

Moonshot AI

Moonshotai/Kimi-K2.5

Kimi multimodal agent model for visual understanding, coding, and planning

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$0.45 per 1M tokens
Cheapest paid output
$2.25 per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

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

Local hardware estimate

At 4K context: Q4_K_M 629.5 GiB, Q8_0 1107.7 GiB, F16 2004.2 GiB working memory.

Parameters
1026.9 billion
Architecture
kimik25
Model license
other

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Observed price history

  • 2026-08-24: $0.45 input / $2.25 output per 1M tokens

API providers

  • SiliconFlow — model id moonshotai/Kimi-K2.5; $0.45 input / $2.25 output per 1M tokens; provider documentation
  • Qiniu — model id moonshotai/kimi-k2.5; not published input / not published output per 1M tokens; provider documentation