ModelBeat
Models/Kimi K2.7 Code
All models
M

Moonshot: Kimi K2.7 Code

Watch this modelCompareFind source
moonshotai/kimi-k2.7-code

Kimi K2.7 Code is Moonshot’s open-weights AI model, released Jun 12, 2026. It costs $0.95/M input and $4/M output tokens, and handles a 262K-token context window. Its strongest use case is math, where it ranks in the 69th percentile of the models Model Beat tracks.

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.

Context
262K
Input
$0.95 / 1M
Output
$4 / 1M
Cheapest via SiliconFlow
$0.86 / $3.80 / 1M
Released
Jun 12, 2026
Modalities
textimage→text
Strongest atMath top 31%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Kimi K2.7 Code lands among all models tracked on Model Beat.

57.0
Intelligence Index
Epoch AI
57th percentile of tracked models
55.0
Coding Index
Epoch AI
55th percentile of tracked models
55.0
Agentic Index
Epoch AI
55th percentile of tracked models

Reasoning

5 evals
GPQA Diamond87.9%

Graduate-level scientific reasoning

Humanity's Last Exam35.0%

Frontier of human expert knowledge

SimpleBench57.9%

Common-sense trick questions

SimpleQA Verified36.5%

Factual accuracy & hallucination

WeirdML54.1%

Novel ML problem-solving

Coding

2 evals
SciCode47.8%

Scientific research coding

WebDev Arena1473

Human-rated web development

Math

1 evals
AIME 2024/202595.6%

Olympiad-qualifier math

Agentic & Tools

2 evals
APEX37.6%

Multi-step agentic tasks

τ²-bench90.1%

Tool-agent-user reliability

Changelog

9
  • Kimi K2.7 Code: reported APEX score rose from 27.6% to 37.6% (+36%)benchmark · Sep 22, 2026
  • Kimi K2.7 Code: cheapest credible provider via SiliconFlow now $0.8592 per 1M input tokens (was $0.69, +25%)cheapest provider · Sep 5, 2026
  • Kimi K2.7 Code: cheapest credible provider via SiliconFlow now $3.8 per 1M output tokens (was $3.49, +9%)cheapest provider · Sep 5, 2026
  • Kimi K2.7 Code: reported SimpleQA Verified score fell from 39.2% to 36.5% (-7%)benchmark · Aug 28, 2026
  • Kimi K2.7 Code: vendor list price cut from $8 to $4 per 1M output tokens (-50%)list price · Aug 15, 2026
  • Kimi K2.7 Code: vendor list price cut from $1.9 to $0.95 per 1M input tokens (-50%)list price · Aug 15, 2026
  • Kimi K2.7 Code: cheapest credible provider via Ambient now $3.49 per 1M output tokens (was $3.8, -8%)cheapest provider · Aug 14, 2026
  • Kimi K2.7 Code: cheapest credible provider via Ambient now $0.69 per 1M input tokens (was $0.8592, -20%)cheapest provider · Aug 14, 2026
  • Kimi K2.7 Code: Humanity's Last Exam improved from 32.8% to 35.0% (+7%)benchmark · Aug 6, 2026

Compare Kimi K2.7 Code with

Kimi K2.7 Code vs GPT-6 AstraKimi K2.7 Code vs Claude Fable 5Kimi K2.7 Code vs Kimi K3Kimi K2.7 Code vs Gemini 3.7 FlashKimi K2.7 Code vs Grok 4.6

Frequently asked questions

What is Kimi K2.7 Code?

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.

Who created Kimi K2.7 Code?

Kimi K2.7 Code is an AI model developed by Moonshot, part of the Kimi family, released Jun 12, 2026.

How much does Kimi K2.7 Code cost?

Kimi K2.7 Code's list price from Moonshot is $0.95 per million input tokens and $4 per million output tokens. The cheapest credible third-party provider on OpenRouter (SiliconFlow) serves it at $0.86/$3.80 per 1M.

What is Kimi K2.7 Code's context window?

Kimi K2.7 Code supports a context window of up to 262K tokens.

How does Kimi K2.7 Code perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Kimi K2.7 Code scores 95.6% on AIME 2024/2025, 35.0% on Humanity's Last Exam, 87.9% on GPQA Diamond.

Is Kimi K2.7 Code open source?

Kimi K2.7 Code is released with open weights (Open weights (unrestricted)), so the model can be downloaded and self-hosted.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Sep 22, 2026.