NOUMENOpen app
NOUMEN

Moonshot · Frontier

Kimi K3.1 Pro

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 is 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
$2.00
Output
$10.00
Cache read
$0.20
Cache write
$2.00
$4.00 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)
921 tokens
Longer than 69% of 473 models

Side by side

Kimi K3.1 Pro 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 ProMoonshotThis modelKimi K3.1 Pro HighspeedMoonshotRemove
ProviderMoonshotMoonshot
Discovery tierFrontierFrontier
AddedOct 24, 2026Oct 24, 2026
Limits
Context window1.05M1.05M
Average output921 tokens1.3K tokens
Pricing, USD per 1M tokens
Input$2.00Best$4.00
Output$10.00Best$20.00
Cache read$0.20$0.20
Cache write$2.00Best$4.00
Performance
Throughput42.1 tok/s125.1 tok/sBest
Time to first token6.7 sBest8.5 s
Request success (24h)83.0%99.8%Best
Benchmark indexes
Intelligence Index55.155.1
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
Video inputYesYes
Reasoning effortlow, high, maxlow, high, max

Public evaluations

Benchmarks

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

  • Kimi K3.1 Pro
  • Kimi K3.1 Pro Highspeed

Intelligence Index

  • Kimi K3.1 Pro55.1
  • Kimi K3.1 Pro Highspeed55.1

Kimi K3.1 Pro: 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: 73.3%Top
    • Kimi K3.1 Pro Highspeed: 73.3%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Kimi K3.1 Pro: 46.0%Top
    • Kimi K3.1 Pro Highspeed: 46.0%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Kimi K3.1 Pro: 1,678 EloTop
    • Kimi K3.1 Pro Highspeed: 1,678 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Kimi K3.1 Pro: 1,846 EloTop
    • Kimi K3.1 Pro Highspeed: 1,846 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Kimi K3.1 Pro: 31.4%Top
    • Kimi K3.1 Pro Highspeed: 31.4%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Kimi K3.1 Pro: 86.3%Top
    • Kimi K3.1 Pro Highspeed: 86.3%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Kimi K3.1 Pro: 52.5%Top
    • Kimi K3.1 Pro Highspeed: 52.5%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Kimi K3.1 Pro: 67.2%Top
    • Kimi K3.1 Pro Highspeed: 67.2%Top

  • SciCode

    Scientific computing in Python

    • Kimi K3.1 Pro: 60.8%Top
    • Kimi K3.1 Pro Highspeed: 60.8%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Kimi K3.1 Pro: 86.3%Top
    • Kimi K3.1 Pro Highspeed: 86.3%Top

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
42.1 tok/s
Faster than 28% of 260 models
Time to first token
6.7 s
Quicker than 20% of 260 models
Prompt cache hits
96.1%
About $0.27 per 1M input tokens with caching
Request success (24h)
83.0%
Unstable

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 49.0%
  • 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",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Moonshot

Other Moonshot models, starting with the same family.