NOUMENOpen app
NOUMEN

Moonshot · Open weights

Kimi K2 Instruct

Added Jan 1, 2024Open weights

Compare models

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

Loading models…

Use in the app

Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.

  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.40
Output
$1.80

Reference prices as published by the model provider. API example

Specifications

Context window
256K
Max output
8.2K
Average output (7 days)
564 tokens
Longer than 53% of 465 models

Side by side

Kimi K2 Instruct 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 InstructMoonshotThis modelGPT 4.1OpenAIRemove
ProviderMoonshotOpenAI
Discovery tierOpen weightsFrontier
AddedJan 1, 2024Sep 10, 2025
Limits
Context window256K1.05MBest
Max output8.19K32.77KBest
Average output564 tokens29 tokens
Pricing, USD per 1M tokens
Input$0.40Best$2.00
Output$1.80Best$8.00
Cache read—$0.50
Performance
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index12.712.7
Math Index57.0Best34.7
Capabilities
ToolsYesYes
VisionNoYes
Structured outputYesYes
PDF inputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Kimi K2 Instruct
  • GPT 4.1

Intelligence Index

  • Kimi K2 Instruct12.7
  • GPT 4.112.7

Kimi K2 Instruct: Better than 28% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Kimi K2 Instruct: 57.0Top
    • GPT 4.1: 34.7

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Kimi K2 Instruct: 53.0%
    • GPT 4.1: 68.3%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Kimi K2 Instruct: 7.4%Top
    • GPT 4.1: 4.2%

  • GPQA Diamond

    Graduate-level science questions

    • Kimi K2 Instruct: 76.6%Top
    • GPT 4.1: 66.6%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Kimi K2 Instruct: 82.4%Top
    • GPT 4.1: 80.6%

  • IFBench

    Following precise output instructions

    • Kimi K2 Instruct: 41.5%
    • GPT 4.1: 43.0%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Kimi K2 Instruct: 55.6%Top
    • GPT 4.1: 45.7%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Kimi K2 Instruct: 57.0%Top
    • GPT 4.1: 34.7%

  • AIME

    Competition mathematics

    • Kimi K2 Instruct: 69.3%Top
    • GPT 4.1: 43.7%

  • MATH-500

    Competition math problems

    • Kimi K2 Instruct: 97.1%Top
    • GPT 4.1: 91.3%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Kimi K2 Instruct: 15.9%Top
    • GPT 4.1: 13.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Kimi K2 Instruct: 61.1%Top
    • GPT 4.1: 47.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Kimi K2 Instruct: 53.0%
    • GPT 4.1: 68.3%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.

Prompt cache hits
67.0%

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.

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

Moonshot

Other Moonshot models, starting with the same family.