DataLearner logo
KI

Kimi K2.7 Code

Coding modelKimi K2

Kimi-K2.7-Code

Release date: 2026-06-12Updated: 2026-08-22Views: 2,500
Live demoGitHubHugging FaceCompare
Parameters
1T
Context length
256K
Multilingual
Supported
Reasoning ability
4/5

Kimi K2.7 Code is a coding model from Moonshot AI, released on 2026-06-12. It accepts text, image, and video input and returns text output. The cataloged parameter count is 1T, with 32B active parameters per inference. The recorded context window is 256K. Cataloged capabilities include Reasoning model, Multilingual, and Coding model. The checkpoint is listed under the Modified Mit license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

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

Kimi K2.7 Code

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Mode (Default)
Context length
256K tokens
Max output length
No data
Model type
Coding model
Modality (in / out)
Text, Image, Video → Text
Release date
2026-06-12
Model file size
595GB
MoE architecture
Yes
Total params / Active params
1T / 32B
Knowledge cutoff
No data
Kimi K2.7 Code

Open source & experience

Code license
Modified MIT
Weights license
Modified MIT- Commercial use permitted
GitHub repo
github.com/MoonshotAI/Kimi-K2
Hugging Face
huggingface.co/moonshotai/Kimi-K2.7-Code
Live demo
kimi.com/code
Kimi K2.7 Code

Official resources

Paper
Paper
DataLearnerAI blog
N/A
Kimi K2.7 Code

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
Text-$0.950/ 1M tokens$4.00/ 1M tokens
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-—$0.190/ 1M tokens

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Kimi K2.7 Code

Benchmark Results

Kimi K2.7 Code currently shows benchmark results led by Terminal Bench Hard (35 / 244, score 44.70), GPQA Diamond (93 / 463, score 89.60), τ²-Bench - Telecom (66 / 264, score 90.10). 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

3 evaluations
Benchmark / mode
Score
Rank/total
LiveBench
Standard Mode
68.41
46 / 117
HLE
Thinking Mode
35
172 / 565
CritPt
Thinking Mode
10
71 / 201

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Thinking Mode
89.60
93 / 463

Common Sense Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleBench
Thinking Mode
57.90
38 / 93

Agent Level Benchmark

3 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Thinking ModeTools
90.10
66 / 264
Terminal Bench Hard
Thinking ModeTools
44.70
35 / 244
τ³-Banking
Thinking ModeTools
20.20
93 / 167

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Thinking Mode
63.10
110 / 282

AI Agent - Tool Usage

4 evaluations
Benchmark / mode
Score
Rank/total
MCPMark-Verified
Thinking ModeTools
81.10
5 / 8
MCP-Atlas
Thinking ModeTools
76
22 / 44
Terminal-Bench 2.1
Thinking ModeTools
67.04
94 / 194
Terminal-Bench 4.0
Thinking ModeTools
1
76 / 88

Coding and Software Engineer

5 evaluations
Benchmark / mode
Score
Rank/total
Kimi Code Bench 2.0
Thinking ModeTools
62
2 / 3
Program Bench
Thinking ModeTools
53.60
4 / 12
SciCode
Thinking Mode
47.80
78 / 131
MLS Bench
Thinking ModeTools
35.10
5 / 6
DeepSWE
Standard ModeTools
31
78 / 86

Productivity Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
Harvey Lab-AA
Thinking ModeTools
85.02
22 / 43

Multimodal Understanding

1 evaluations
Benchmark / mode
Score
Rank/total
GDP.pdf
Thinking Mode
11.20
74 / 119

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
PinchBench v2
unknown
76.11
14 / 45
View benchmark analysisCompare with other models

Compare with other models

Kimi K2.7 Code

Publisher

Kimi-K2.7-Code

Model Overview

Kimi K2.7 Code is a coding model from Moonshot AI, released on 2026-06-12.

It accepts text, image, and video input and produces text output. Its cataloged capabilities include Reasoning model, Multilingual, and Coding model. The cataloged parameter count is 1T, with 32B active parameters per inference. The recorded context window is 256K.

The checkpoint is listed under the Modified Mit license, with the license link included in the model references. The page records 4 API pricing rules from Moonshot AI; current provider pricing and conditions should be checked before deployment. The evaluation section contains 3 cataloged benchmark results with their recorded modes and scores. The page links 4 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

Kimi K2.7 Code

FAQ

What is Kimi K2.7 Code?

Kimi K2.7 Code is a coding model from Moonshot AI, released on 2026-06-12. It accepts text, image, and video input and returns text output. The cataloged parameter count is 1T, with 32B active parameters per inference. The recorded context window is 256K. Cataloged capabilities include Reasoning model, Multilingual, and Coding model. The checkpoint is listed under the Modified Mit license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does Kimi K2.7 Code support?

The current model record lists text, image, and video as input and text as output.

What are the main recorded specifications for Kimi K2.7 Code?

The cataloged parameter count is 1T, with 32B active parameters per inference. The recorded context window is 256K. Fields without a source-backed value remain undisclosed.

Does Kimi K2.7 Code have API pricing?

The page records 4 API pricing rules from Moonshot AI; current provider pricing and conditions should be checked before deployment.

Are benchmark results available for Kimi K2.7 Code?

The evaluation section contains 3 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is Kimi K2.7 Code open source?

The checkpoint is listed under the Modified Mit license, with the license link included in the model references. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

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

DataLearner WeChat QR code