NOUMENOpen app
NOUMEN

Moonshot · Open weights

Kimi K2.6 TEE

Added Apr 21, 2026Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

Kimi K2.6 is Moonshot AI's next-generation multimodal model designed for long-horizon coding and agentic orchestration. Running inside a TEE (Trusted Execution Environment), with provider attestation support.

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

Pricing

USD per 1M tokens
Input
$1.50
Output
$5.25
Cache read
$0.38

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
65.5K
Average output (7 days)
3.1K tokens
Longer than 97% of 473 models

Side by side

Compare models

Put Kimi K2.6 TEE next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryGrok Build 0.1Solar Pro 4GLM 5 TurboAll 3

Public evaluations

Benchmarks

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

Intelligence Index

27.0

Better than 68% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    61.8

    Composite of the coding evaluations

    Better than 63% of 168 scored models

Agentic work

  • AutomationBench-AA

    13.0%

    Workflow automation, penalized for guardrail violations

    Better than 33% of 173 scored models

  • AutomationBench-AA tasks completed

    1.8%

    Workflows finished end to end without a guardrail violation

    Better than 34% of 173 scored models

  • AA-Briefcasev1.1

    819 Elo

    Agentic knowledge work, rated head to head

    Better than 30% of 166 scored models

  • GDPval-AAv2.1

    1,038 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 40% of 187 scored models

Document reasoning

  • GDP.pdf

    13.0%

    Professional reasoning over PDF documents, all-pass rate

    Better than 58% of 171 scored models

  • AA-LCRv1.1

    81.0%

    Reasoning across long documents

    Better than 84% of 309 scored models

  • MLCR-AA

    11.1%

    Long-context reasoning over medical records

    Better than 38% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    37.5%

    Expert-level questions across academic fields

    Better than 71% of 323 scored models

  • GPQA Diamond

    91.1%

    Graduate-level science questions

    Better than 81% of 291 scored models

  • IFBench

    76.0%

    Following precise output instructions

    Better than 88% of 215 scored models

Coding

  • Terminal-Benchv4.0

    0.5%

    Practical software engineering in a terminal

    Better than 30% of 171 scored models

  • SciCode

    51.5%

    Scientific computing in Python

    Better than 59% of 174 scored models

Legacy evaluations

  • Terminal-Bench Hard

    43.9%

    Earlier terminal task suite

    Better than 85% of 212 scored models

  • τ²-Bench Telecom

    95.9%

    Tool use in a customer-support simulation

    Better than 90% of 214 scored models

  • AA-LCR (unversioned)

    81.0%

    Long-context reasoning, earlier grading

    Better than 84% of 309 scored models

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

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Prompt cache hits
0.0%
About $1.50 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 33.3%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

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-k2.6",
    "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-k2.6",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Moonshot

Other Moonshot models, starting with the same family.