MA

Kimi K2 Thinking

LLMby Moonshot AI·Model page ↗

Moonshot AI's reasoning LLM with a 262K-token context for complex problem-solving.

Max output

Most tokens the model can return in a single response.

100Ktokens
Reasoning
Reasoning-first model

Works through a step-by-step chain of thought before answering.

Share:

Design Arena

Design Arena ranks models on real-world front-end and design tasks — websites, UI components, data viz, SVG and more — through head-to-head human votes, scored as an ELO rating.
CategoryELOWin rateRank
Website114448.8%#76

Pricing

per 1M tokens
Input$0.6 /1M
Output$2.5 /1M
Cache read$0.15 /1M

Model Description

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

Author
MA
Moonshot AI
Organization
moonshotai
Details
Downloads—
Likes—
AccessOpen Source
Context262K tokens
Input price$0.6 /1M
Output price$2.5 /1M
CreatedNov 6, 2025
Updated—
View on Hugging Face
Benchmarks
Intelligence17.3
Coding21.0
Agentic1.8
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Kimi K2 Thinking — AI Model Details | Applied