Back to the index
Moonshot AI · Kimi
No. 36

Kimi K2 Thinking

Deep-reasoning open variant of Kimi K2 for hard problems.

ReasoningOpen weightsText
Field notes
Context window
262Ktokens
Max output
66Ktokens
Input price
$0.60/ 1M tokens
Output price
$2.50/ 1M tokens
Cached input
$0.15/ 1M tokens
Modalities
Text
Knowledge cutoff
Apr 2025
Released
Nov 2025
Parameters
1000B
License
Modified MIT
Approx. speed
Overview

What this model is

Kimi K2 Thinking is Moonshot's dedicated reasoning checkpoint (1T MoE, 32B active, Modified MIT) that extends test-time thinking and tool use for hard math, logic, and research tasks. It posts strong reasoning scores and long tool-call chains, but is slower and from the earlier K2 generation than K2.6. A capable open reasoner rather than a frontier agentic coder.

Strengths

  • Strong deep-reasoning and tool-use scores
  • Long tool-call chains for research
  • Open Modified MIT weights, INT4-efficient
  • Competitive math (AIME) performance

Trade-offs

  • Slow due to extended thinking
  • Older K2 generation than K2.6
  • Agentic-coding reliability below the frontier
  • Text-only input

Best for

  • Hard math and logic problems
  • Tool-augmented research agents
  • Reasoning-heavy analysis
  • Self-hosted reasoning

Not ideal for

  • Latency-sensitive workloads
  • Long autonomous production coding
Capabilities

Capability profile

Normalized 0–100 scores, comparable across the whole catalog.

Reasoning84Coding72Math88Writing76Knowledge80Speed45Agentic68Vision5Multilingual76Long Context80
Reasoning
84
Coding
72
Math
88
Writing
76
Knowledge
80
Speed
45
Agentic
68
Vision
5
Multilingual
76
Long Context
80
Benchmarks

How it scores

Public benchmark results, with independent third-party results where available. Bars normalize percentages to 100 and Elo ratings to a 1500 ceiling.

BenchmarkResult
GPQA Diamondindependent
ReasoningIndependent aggregators
84.5%
AIME 2025
MathVendor-reported
94%
Alternatives

Comparable models

Models in a roughly similar class — worth weighing against this one.