Moonshot AI

Kimi K2.7 Code

Benchmarks, price, context and versions

Also searched as

Kimi-K2.7-Code

Direct answer: Kimi K2.7 Code is a model from Moonshot AI. 87.9% on GPQA Diamond, per Epoch AI. On OpenRouter, US$ 0.60 per 1 million input tokens and US$ 3.50 per 1 million output tokens.

✓ Good for

  • calculation and problems with an exact answer (#42 of 186 on OTIS Mock AIME)
  • technical reasoning as the model appears through the API (#30 of 135 on GPQA Diamond (OpenRouter))
  • agents that follow rules and use tools (#26 of 131 on τ-bench Verified (airline))
  • running on your own infrastructure (open weights)

✕ Not the best for

  • the ceiling of reasoning on research-level math (#51 of 86 on FrontierMath (tiers 1 to 3))
  • answering short facts with little invention (#54 of 87 on SimpleQA Verified)

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

Benchmarks

GPQA Diamond

?what it is
87.9%

highest score on this metric 96.4%

58º / 198 · Epoch AI, latest version we checked

OTIS Mock AIME

?
95.6%

highest score on this metric 100%

42º / 186 · Epoch AI, latest version we checked

FrontierMath (tiers 1 to 3)

?
54%

highest score on this metric 95.1%

51º / 86 · Epoch AI, latest version we checked

SimpleQA Verified

?
36.5%

highest score on this metric 94%

54º / 87 · Epoch AI, latest version we checked

GPQA Diamond (OpenRouter)

?
90.9%

highest score on this metric 96.5%

30º / 135 · OpenRouter Benchmarks, latest version we checked

τ-bench Verified (airline)

?
77.3%

highest score on this metric 82%

26º / 131 · OpenRouter Benchmarks, latest version we checked

Key specs

Origin
China
Family
Kimi Code provisional data
Weights?
open
License
other
Input US$/1M?
US$ 0.60
Output US$/1M
US$ 3.50
Context?
262,144 tokens
Parameters
1,026,879,376,368
Input
image, text
OpenRouter usage?
no data
Downloads (30 days)?
91,687
Use cases provisional data
Text Agents Code
Dates in sources
  • 2026, published, per Epoch AI
  • 2026, listed on OpenRouter
  • 2026, Hugging Face repo created

Version history

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

FAQ

What is Kimi K2.7 Code?

Kimi K2.7 Code is a model from Moonshot AI, with open weights, used for text, agents, code.

How much does Kimi K2.7 Code cost?

On OpenRouter, US$ 0.60 per 1 million input tokens and US$ 3.50 per 1 million output tokens.

What is the context window of Kimi K2.7 Code?

262,144 tokens, per OpenRouter.

Is Kimi K2.7 Code open source?

Yes, it has open weights. License: other.

What is Kimi K2.7 Code's GPQA Diamond score?

87.9% on GPQA Diamond, per Epoch AI.

Is Kimi K2.7 Code good for coding?

No data: there is no SWE-bench Verified measurement for it in open sources.

Who made Kimi K2.7 Code?

It was made by Moonshot AI, a lab from China.

provisional data Questions under review: Semrush had no API balance during collection. Answers use source data only.

Models from Moonshot AI

See lab

Sources

  • Epoch AI, CC BY 4.0, latest version we checked.
  • Hugging Face Hub, metadados públicos do Hub; licença de cada modelo no repositório, latest version we checked.
  • OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
  • OpenRouter Benchmarks, CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.