Toggle navigation

Moonshot AI

Available in Shortly AI

Kimi K3

Released July 16, 2026

ReasoningVision (Image)Tool Use

Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.

Context window
1M tokens
Maximum output
131.1K tokens
Input pricing
$3.00/M
Output pricing
$15.00/M

Independent benchmark

LiveBench performance

79.2overall

Benchmark data from LiveBench, release 2026-06-25. Scores are pinned and are not fetched on page load.

Kimi K3 LiveBench category scores
CategoryScore
Reasoning90.673
Coding81.446
Agentic Coding62.172
Mathematics84.437
Data Analysis78.734
Language85.528
Instruction Following71.363

Benchmarks measure selected evaluation tasks and do not guarantee performance for every prompt or workflow.

FAQ

Similar AI models

Available with one subscription

Start with Kimi K3 in Shortly AI

Keep your conversations, files and model choices together in one workspace.