NOUMENOpen app
NOUMEN

Moonshot · Open weights

Kimi K2.7 Code TEE

Added Aug 15, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode while running inside a Trusted Execution Environment (TEE) with attestation support.

  • Reasoning
  • Tools
  • Vision
  • Parallel tools
Input
Text, Images
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.95
Output
$4.00
Cache read
$0.19

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
65.5K
Average output (7 days)
1.1K tokens
Longer than 75% of 473 models

Side by side

Kimi K2.7 Code TEE compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Kimi K2.7 Code TEEMoonshotThis modelInkling SmallthinkingmachinesRemove
ProviderMoonshotthinkingmachines
Discovery tierOpen weightsOpen weights
AddedAug 15, 2026Jul 31, 2026
Limits
Context window262.14K524.29KBest
Max output65.54KBest32.77K
Average output1.1K tokens577 tokens
Pricing, USD per 1M tokens
Input$0.95$0.45Best
Output$4.00$1.20Best
Cache read$0.19$0.10Best
Benchmark indexes
Intelligence Index25.8Best25.7
Coding Index60.8Best52.9
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesYes
Audio inputNoYes
Parallel toolsYesNo
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Kimi K2.7 Code TEE
  • Inkling Small

Intelligence Index

  • Kimi K2.7 Code TEE25.8
  • Inkling Small25.7

Kimi K2.7 Code TEE: Better than 63% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Kimi K2.7 Code TEE: 60.8Top
    • Inkling Small: 52.9

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Kimi K2.7 Code TEE: 24.5%Top
    • Inkling Small: 4.8%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Kimi K2.7 Code TEE: 4.7%Top
    • Inkling Small: 0.6%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Kimi K2.7 Code TEE: —
    • Inkling Small: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Kimi K2.7 Code TEE: 858 Elo
    • Inkling Small: 911 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Kimi K2.7 Code TEE: 1,038 Elo
    • Inkling Small: 1,124 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Kimi K2.7 Code TEE: 11.2%Top
    • Inkling Small: 11.2%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Kimi K2.7 Code TEE: 79.3%Top
    • Inkling Small: 75.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • Kimi K2.7 Code TEE: 12.2%Top
    • Inkling Small: 7.8%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Kimi K2.7 Code TEE: 35.0%Top
    • Inkling Small: 33.3%

  • GPQA Diamond

    Graduate-level science questions

    • Kimi K2.7 Code TEE: 89.6%Top
    • Inkling Small: 89.5%

  • IFBench

    Following precise output instructions

    • Kimi K2.7 Code TEE: 63.1%
    • Inkling Small: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Kimi K2.7 Code TEE: 1.0%Top
    • Inkling Small: 1.0%Top

  • SciCode

    Scientific computing in Python

    • Kimi K2.7 Code TEE: 47.8%
    • Inkling Small: 49.7%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Kimi K2.7 Code TEE: 44.7%
    • Inkling Small: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Kimi K2.7 Code TEE: 90.1%
    • Inkling Small: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Kimi K2.7 Code TEE: 79.3%Top
    • Inkling Small: 75.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "TEE/kimi-k2.7-code",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="TEE/kimi-k2.7-code",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Moonshot

Other Moonshot models, starting with the same family.