HomeModelsMoonshot Kimi K3.7 (512k)

Moonshot Kimi K3.7 (512k)

Moonshot AI 512K context Released: 2026-07

Moonshot's flagship Kimi K3.7, an open-weight mixture-of-experts model with a 512K token window. K3.7 closes most of the gap to Western frontier models on agentic coding while staying dramatically cheaper.

Visit Model Website

Pricing Information

Input Pricing

Standard:$0.6000
Per 1,000 tokens
Cached:$0.0600
Per 1,000 tokens (cached requests)

Output Pricing

Standard:$2.5000
Per 1,000 tokens

Example Costs

Short Conversation
1K input + 500 output tokens
$1.8500
Book Analysis
50K input + 2K output tokens
$35.00

Token Calculator

Tokens:0
Words:0
Characters:0
Input Cost:$0.00
Estimated based on current token count as input
Use our main calculator for more detailed estimates including input/output combinations.

Key Features

  • 512K token context window
  • Open-weight MoE architecture
  • Strong agentic tool use
  • Aggressive price per token
  • Native long-horizon planning

Common Use Cases

  • Agentic coding
  • Long-context research
  • Cost-sensitive production
  • Self-hosted deployments

Ratings & Feedback

0.0 / 5 · 0 votes

Comments

Frequently Asked Questions

What is a token in the context of Large Language Models (LLMs)?

Why is understanding token count important for using LLMs?

What factors affect LLM pricing?

What is a context window in LLMs?

How can I optimize my prompts to use fewer tokens?