LLM Pricing

← All Models

MoonshotAI: Kimi K2 Thinking

🇨🇳 Moonshot AI · Kimi K2

Input Price $0.600 per million tokens NT$19.2
Output Price $2.50 per million tokens NT$80.0
Context Window 262K tokens Output limit: 100K
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

MoonshotAI: Kimi K2 Thinking is a large language model API from Moonshot AI, part of its Kimi K2 model family. Priced at $0.600 per million input tokens and $2.50 per million output tokens, it occupies the mid-range, balancing capability against running cost. Output tokens cost about 4× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. A large 262K-token context window (≈393 pages of text) lets it take in whole books, large codebases, or lengthy transcripts in a single call. On Artificial Analysis's Intelligence Index it scores 33 (C grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
Input per 1M tokens $0.600 NT$19.2
Output per 1M tokens $2.50 NT$80.0
Cached Input per 1M tokens $0.150 NT$4.8

Provider
Moonshot AI
Model Family
Kimi K2
Version String
moonshotai/kimi-k2-thinking
Status
Active
Modality
Text
Context Window
262,144 tokens
Output Limit
100,352 tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Intelligence Index 33 C Measured: 2026-07-01

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 66.3% B Measured: 2026-07-01
GPQA Diamond 83.8% A Measured: 2026-07-01
HLE 22.3% A Measured: 2026-07-01
IFBench 68.1% B Measured: 2026-07-01
Non-Hallucination 27.8% Measured: 2026-07-01
Omniscience Accuracy 30.0% Measured: 2026-07-01
SciCode 42.4% B Measured: 2026-07-01
Tau2 93.0% Measured: 2026-07-01
TerminalBench 31.1% Measured: 2026-07-01

Performance Metrics

Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis

First Token Latency 1.3s Measured: 2026-07-01
Output Speed 125 t/s Measured: 2026-07-01
Response Time 21.3s Measured: 2026-07-01

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Cached Input $0.150 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Cached Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter
Output $2.50 OpenRouter
Input $0.600 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • MoonshotAI: Kimi K2 Thinking Input price: $0.6/M tokens
  • MoonshotAI: Kimi K2 Thinking Output price: $2.5/M tokens
  • Context window: 262,144 tokens
  • Provider: Moonshot AI
  • Model family: Kimi K2
  • Modalities: Text
  • Data source: OpenRouter, updated daily