DataLearner logo
KI

Kimi K2 Thinking

Reasoning modelKimi K2Kimi K2

Kimi K2 Thinking

Release date: 2025-11-06Updated: 2026-06-15 07:18:24.2152,636
Parameters
1T
Context length
256K
Chinese support
Supported
Reasoning ability

Kimi K2 Thinking is an AI model published by Moonshot AI, released on 2025-11-06, for Reasoning model, with 1T parameters, and 256K context length, requiring about 1.09 TB storage, under the Modified MIT License license, with a 100.00 score on AIME2025.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Kimi K2 Thinking

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
256K tokens
Max output length
No data
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2025-11-06
Model file size
1.09 TB
MoE architecture
Yes
Total params / Active params
1T / 32B
Knowledge cutoff
No data
Kimi K2 Thinking

Open source & experience

Kimi K2 Thinking

Official resources

Kimi K2 Thinking

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.600/ 1M$2.50/ 1M
Batch
TypeConditionInputOutput
Text-$0.300/ 1M$1.25/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-$0.600/ 1M$0.300/ 1M
Kimi K2 Thinking

Benchmark Results

Kimi K2 Thinking currently shows benchmark results led by AIME2025 (1 / 106, score 100), Terminal-Bench (4 / 35, score 47.10), HLE (21 / 168, score 51). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

6 evaluations
Benchmark / mode
Score
Rank/total
84.60
32 / 126
84.50
56 / 182
LiveBench
Thinking Mode
61.59
63 / 115
51
21 / 168
44.90
40 / 168
23.90
104 / 168

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
83.10
22 / 120
71.30
53 / 110

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
100
1 / 106
99.10
12 / 106
94.50
27 / 106
0
72 / 80

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
47.10
4 / 35

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
Standard Mode
39.60
41 / 63

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
68
18 / 30

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
60.20
35 / 51

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Claw Bench
Thinking ModeTools
82.50
17 / 29

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Kimi K2 Thinking

Publisher

Kimi K2 Thinking

Model Overview

Kimi K2 Thinking is an AI model published by Moonshot AI, released on 2025-11-06, for Reasoning model, with 1T parameters, and 256K context length, requiring about 1.09 TB storage, under the Modified MIT License license, with a 100.00 score on AIME2025.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code