MoonshotAI Models
MoonshotAI logo

Kimi K2.5

by MoonshotAI

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.

Chat with Kimi K2.5
Input Price$0.60/1M tokens
Output Price$3.00/1M tokens
Intelligence46.7
Coding39.5

Specifications

Technical details and pricing.

ProviderMoonshotAI
Context Window262,144 tokens
Release DateJan 27, 2026
ModalitiesText, Image → Text
CapabilitiesVision

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA87.9%
HLE29.4%
SciCode49.0%
LCR65.3%
IFBench70.2%
Tau295.9%
TerminalBench Hard34.8%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is Kimi K2.5 good for?

Use Kimi K2.5 for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Kimi K2.5 cost?

Pricing is based on usage. Current rates are $0.60/1M tokens for input and $3.00/1M tokens for output.

Can I try Kimi K2.5 for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Kimi K2.5 support images or audio?

Kimi K2.5 can understand images.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.