NOUMENOpen app
NOUMEN

Moonshot · Frontier

Kimi K3.1 Pro Highspeed

Added Oct 24, 2026

Compare models

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

Loading models…

Use in the app

Kimi K3.1 Pro Highspeed is the faster variant of K3.1 Pro, a multimodal reasoning model for coding, 3D creation, document analysis and multi-step tool use. It supports a 1M-token context window and text, image and video inputs. Reasoning is always enabled, with low, high and max effort levels.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Video input
Input
Text, Images, Video
Output
Text
Reasoning effort
low · high · max
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$4.00
Output
$20.00
Cache read
$0.20
Cache write
$4.00
$8.00 for a 1-hour cache

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
—
Average output (7 days)
1.3K tokens
Longer than 80% of 473 models

Side by side

Kimi K3.1 Pro Highspeed 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 K3.1 Pro HighspeedMoonshotThis modelMuse WonderMetaRemove
ProviderMoonshotMeta
Discovery tierFrontierFrontier
AddedOct 24, 2026Oct 12, 2026
Limits
Context window1.05M1.05M
Average output1.3K tokens1.2K tokens
Pricing, USD per 1M tokens
Input$4.00$4.00
Output$20.00$20.00
Cache read$0.20$0.20
Cache write$4.00—
Performance
Throughput125.1 tok/sBest102.6 tok/s
Time to first token8.5 s1.8 sBest
Request success (24h)99.8%Best99.5%
Benchmark indexes
Intelligence Index55.1Best52.4
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputNoYes
Audio inputNoYes
Video inputYesYes
Reasoning effortlow, high, maxminimal, low, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • Kimi K3.1 Pro Highspeed
  • Muse Wonder

Intelligence Index

  • Kimi K3.1 Pro Highspeed55.1
  • Muse Wonder52.4

Kimi K3.1 Pro Highspeed: Better than 99% of 326 scored models

3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Kimi K3.1 Pro Highspeed: 73.3%Top
    • Muse Wonder: 68.1%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Kimi K3.1 Pro Highspeed: 46.0%Top
    • Muse Wonder: 39.1%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Kimi K3.1 Pro Highspeed: —
    • Muse Wonder: 10.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Kimi K3.1 Pro Highspeed: 1,678 EloTop
    • Muse Wonder: 1,659 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Kimi K3.1 Pro Highspeed: 1,846 EloTop
    • Muse Wonder: 1,770 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Kimi K3.1 Pro Highspeed: 31.4%Top
    • Muse Wonder: 30.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • Kimi K3.1 Pro Highspeed: 86.3%Top
    • Muse Wonder: 80.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • Kimi K3.1 Pro Highspeed: —
    • Muse Wonder: 22.2%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Kimi K3.1 Pro Highspeed: 52.5%Top
    • Muse Wonder: 50.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Kimi K3.1 Pro Highspeed: 67.2%Top
    • Muse Wonder: 52.0%

  • SciCode

    Scientific computing in Python

    • Kimi K3.1 Pro Highspeed: 60.8%Top
    • Muse Wonder: 60.3%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Kimi K3.1 Pro Highspeed: 86.3%Top
    • Muse Wonder: 80.7%

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.

Throughput
125.1 tok/s
Faster than 71% of 260 models
Time to first token
8.5 s
Quicker than 15% of 260 models
Prompt cache hits
97.2%
About $0.31 per 1M input tokens with caching
Request success (24h)
99.8%
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 91.3%
  • 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": "moonshotai/kimi-k3.1-pro-highspeed",
    "reasoning_effort": "low",
    "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-k3.1-pro-highspeed",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Moonshot

Other Moonshot models, starting with the same family.