Skip to content
LLMs
Moonshot AI logo

MoonshotAI: Kimi K2 Thinking

by Moonshot AI

MoonshotAI: Kimi K2 Thinking is a large language model from Moonshot AI. It costs $0.600 per million input tokens and $2.50 per million output tokens. Its context window is 262K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weights
Input / 1M tokens
$0.600
Output / 1M tokens
$2.50
Cached input / 1M
$0.150

On repeated prefixes

Context window
262K

tokens

Who serves it cheapest

2 hosts serve Kimi K2 Thinking. Same weights, same API - the price difference is pure margin and routing.

Providers serving MoonshotAI: Kimi K2 Thinking, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
GoogleCheapest$0.600$2.50262K-100.0%
Novitabf16$0.600$2.50262K-99.9%

The spread between Google and Novita is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Coding index
21.0

About Kimi K2 Thinking

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...

Specifications

MoonshotAI: Kimi K2 Thinking specifications
Model IDmoonshotai/kimi-k2-thinking
ProviderMoonshot AI
Context window262K tokens
Max output98K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - moonshotai/Kimi-K2-Thinking
ReleasedNovember 6, 2025

Cheaper alternatives

Models that cost less than Kimi K2 Thinking while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does MoonshotAI: Kimi K2 Thinking cost?

$0.600 per million input tokens and $2.50 per million output tokens. Cached input reads cost $0.150 per million tokens.

What is the context window of MoonshotAI: Kimi K2 Thinking?

262K tokens, with up to 98K tokens of output per request.

Which provider serves MoonshotAI: Kimi K2 Thinking cheapest?

Google at $0.600 per million input tokens - about the same cheaper than Novita, the most expensive of the 2 hosts serving it.

Confirm against the source: Moonshot AI official pricing.