moonshotai

MoonshotAI: Kimi K2 Thinking

The Kimi K2 Thinking AI from MoonshotAI is designed for text-based input modalities and has a context length of 262144 tokens. It supports tools and reasoning tasks. For users who require robust text analysis capabilities at a moderate price point, the Kimi K2 Thinking model may be worth considering. Its blended benchmark score of 54.6 across one independent benchmark suggests decent performance in specific use cases. However, it comes with a higher output token cost compared to other models, which could offset its suitability for heavy usage scenarios.

Quality Score
98/100
price + capability + benchmarks
Input Price
$0.60
per 1M tokens · checked 2026-09-04
Output Price
$2.50
per 1M tokens · checked 2026-09-04
Context Window
262,144
tokens

Benchmark results

Independent, published benchmarks. Blended score 54.6 across 1 benchmark, last refreshed 2026-09-04. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 55.3
Model ID
moonshotai/kimi-k2-thinking
Vendor
moonshotai
Released
November 2025
Tokenizer
Other
Input Modalities
text
Output Modalities
text
Max Output
100,352 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.60/M input and $2.50/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.02
Classify 1,000 customer emails 500k in / 50k out $0.42
A month of a busy support chatbot 5M in / 2M out $8.00

Similar models

Quick answers

How much does MoonshotAI: Kimi K2 Thinking cost?
$0.60 per million input tokens and $2.50 per million output tokens.
What is MoonshotAI: Kimi K2 Thinking's context window?
262,144 tokens, roughly 393 pages of text in a single request.
Does MoonshotAI: Kimi K2 Thinking support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can MoonshotAI: Kimi K2 Thinking process images?
No, it is text-only on the input side.