Toggle navigation

Moonshot AI

Available in Shortly AI

Kimi K2.5

Released January 26, 2026

ReasoningVision (Image)Tool Use

kimi-k2.5 is Kimi's most versatile model to date, featuring a native multimodal architecture that supports both visual and text input, thinking and non-thinking modes, and dialogue and agent tasks.

Context window
262.1K tokens
Maximum output
262.1K tokens
Input pricing
$0.60/M
Output pricing
$3.00/M

Independent benchmark

LiveBench historical snapshot

69.1overall

Historical benchmark data from LiveBench, release 2026-01-08. Scores are pinned and are not fetched on page load.

Kimi K2.5 LiveBench category scores
CategoryScore
Reasoning75.957
Coding77.863
Agentic Coding48.333
Mathematics84.868
Data Analysis61.358
Language77.666
Instruction Following57.413

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 K2.5 in Shortly AI

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