NOUMENOpen app
NOUMEN

Moonshot · Open weights

Kimi K2 0711 Instruct FP4

Added Jan 1, 2024Open weights

Compare models

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

Loading models…

Use in the app

Deprecated. This model now routes to Kimi K2 0711.

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
131.1K
Max output
—

Side by side

Kimi K2 0711 Instruct FP4 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 0711 Instruct FP4MoonshotThis modelKimi K2.6 ThinkingMoonshotRemove
ProviderMoonshotMoonshot
Discovery tierOpen weightsOpen weights
AddedJan 1, 2024Apr 16, 2026
Limits
Context window131.07K262.14KBest
Max output—65.54K
Average output—4K tokens
Pricing, USD per 1M tokens
Input$0.40Best$0.45
Output$1.80Best$1.89
Cache read—$0.0757
Performance
Throughput405.1 tok/sBest40.8 tok/s
Time to first token10.2 s2.9 sBest
Request success (24h)—99.8%
Benchmark indexes
Intelligence Index—27.0
Coding Index—61.8
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Parallel toolsNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Kimi K2 0711 Instruct FP4
  • Kimi K2.6 Thinking

Intelligence Index

  • Kimi K2 0711 Instruct FP4—
  • Kimi K2.6 Thinking27.0
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 61.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 13.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 1.8%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 819 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 1,038 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 13.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 81.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 11.1%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 37.5%

  • GPQA Diamond

    Graduate-level science questions

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 91.1%

  • IFBench

    Following precise output instructions

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 76.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 0.5%

  • SciCode

    Scientific computing in Python

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 51.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 43.9%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 95.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Kimi K2 0711 Instruct FP4: —
    • Kimi K2.6 Thinking: 81.0%

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
405.1 tok/s
Faster than 97% of 250 models
Time to first token
10.2 s
Quicker than 10% of 250 models
Prompt cache hits
56.2%

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": "baseten/Kimi-K2-Instruct-FP4",
    "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="baseten/Kimi-K2-Instruct-FP4",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Moonshot

Other Moonshot models, starting with the same family.