NOUMENOpen app
NOUMEN

Moonshot · Open weights

Kimi K2.7 Code High-Speed

Added Jun 15, 2026Open weights

Compare models

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

Loading models…

Use in the app

Kimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.

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

Pricing

USD per 1M tokens
Input
$1.90
Output
$8.00
Cache read
$0.32

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
65.5K
Average output (7 days)
491 tokens
Longer than 48% of 473 models

Side by side

Compare models

Put Kimi K2.7 Code High-Speed 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…

TryInkling SmallGrok 4.20MiMo V2.5 Pro ThinkingAll 3

Public evaluations

Benchmarks

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

Intelligence Index

25.8

Better than 63% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    60.8

    Composite of the coding evaluations

    Better than 61% of 168 scored models

Agentic work

  • AutomationBench-AA

    24.5%

    Workflow automation, penalized for guardrail violations

    Better than 45% of 173 scored models

  • AutomationBench-AA tasks completed

    4.7%

    Workflows finished end to end without a guardrail violation

    Better than 46% of 173 scored models

  • AA-Briefcasev1.1

    858 Elo

    Agentic knowledge work, rated head to head

    Better than 33% of 166 scored models

  • GDPval-AAv2.1

    1,038 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 39% of 187 scored models

Document reasoning

  • GDP.pdf

    11.2%

    Professional reasoning over PDF documents, all-pass rate

    Better than 47% of 171 scored models

  • AA-LCRv1.1

    79.3%

    Reasoning across long documents

    Better than 73% of 309 scored models

  • MLCR-AA

    12.2%

    Long-context reasoning over medical records

    Better than 47% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    35.0%

    Expert-level questions across academic fields

    Better than 68% of 323 scored models

  • GPQA Diamond

    89.6%

    Graduate-level science questions

    Better than 75% of 291 scored models

  • IFBench

    63.1%

    Following precise output instructions

    Better than 62% of 215 scored models

Coding

  • Terminal-Benchv4.0

    1.0%

    Practical software engineering in a terminal

    Better than 37% of 171 scored models

  • SciCode

    47.8%

    Scientific computing in Python

    Better than 41% of 174 scored models

Legacy evaluations

  • Terminal-Bench Hard

    44.7%

    Earlier terminal task suite

    Better than 86% of 212 scored models

  • τ²-Bench Telecom

    90.1%

    Tool use in a customer-support simulation

    Better than 74% of 214 scored models

  • AA-LCR (unversioned)

    79.3%

    Long-context reasoning, earlier grading

    Better than 73% 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 $1.90 per 1M input tokens with caching
Request success (24h)
99.5%
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 88.8%
  • 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": "moonshotai/kimi-k2.7-code-highspeed",
    "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="moonshotai/kimi-k2.7-code-highspeed",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Moonshot

Other Moonshot models, starting with the same family.