NOUMENOpen app
NOUMEN

OpenAI · Frontier

GPT 4.1

Added Sep 10, 2025

Compare models

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

Loading models…

Use in the app

GPT 4.1 is the new flagship model from OpenAI. Huge context window (1 mln tokens), outperforms GPT-4o and GPT 4.5 across coding and does very well at understanding large contexts.

  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$2.00
Output
$8.00
Cache read
$0.50

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
32.8K
Average output (7 days)
29 tokens
Longer than 1% of 465 models

Side by side

GPT 4.1 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…

GPT 4.1OpenAIThis modelNvidia Nemotron 3 Super 120BnvidiaRemove
ProviderOpenAInvidia
Discovery tierFrontierOpen weights
AddedSep 10, 2025Mar 1, 2026
Limits
Context window1.05MBest262.14K
Max output32.77KBest16.38K
Average output29 tokens431 tokens
Pricing, USD per 1M tokens
Input$2.00$0.05Best
Output$8.00$0.25Best
Cache read$0.50—
Performance
Request success (24h)100.0%Best99.9%
Benchmark indexes
Intelligence Index12.712.8Best
Coding Index—37.7
Math Index34.7—
Capabilities
ReasoningNoYes
ToolsYesNo
VisionYesNo
Structured outputYesNo
PDF inputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • GPT 4.1
  • Nvidia Nemotron 3 Super 120B

Intelligence Index

  • GPT 4.112.7
  • Nvidia Nemotron 3 Super 120B12.8

GPT 4.1: Better than 28% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT 4.1: —
    • Nvidia Nemotron 3 Super 120B: 37.7

  • Math Index

    Composite of the math evaluations

    • GPT 4.1: 34.7
    • Nvidia Nemotron 3 Super 120B: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT 4.1: —
    • Nvidia Nemotron 3 Super 120B: 3.8%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT 4.1: —
    • Nvidia Nemotron 3 Super 120B: 0.3%

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 4.1: —
    • Nvidia Nemotron 3 Super 120B: 490 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT 4.1: —
    • Nvidia Nemotron 3 Super 120B: 2.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 4.1: 68.3%Top
    • Nvidia Nemotron 3 Super 120B: 65.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 4.1: 4.2%
    • Nvidia Nemotron 3 Super 120B: 20.8%Top

  • GPQA Diamond

    Graduate-level science questions

    • GPT 4.1: 66.6%
    • Nvidia Nemotron 3 Super 120B: 80.0%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT 4.1: 80.6%
    • Nvidia Nemotron 3 Super 120B: —

  • IFBench

    Following precise output instructions

    • GPT 4.1: 43.0%
    • Nvidia Nemotron 3 Super 120B: 71.5%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT 4.1: —
    • Nvidia Nemotron 3 Super 120B: 0.0%

  • SciCode

    Scientific computing in Python

    • GPT 4.1: —
    • Nvidia Nemotron 3 Super 120B: 36.2%

  • LiveCodeBench

    Recent competitive programming problems

    • GPT 4.1: 45.7%
    • Nvidia Nemotron 3 Super 120B: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT 4.1: 34.7%
    • Nvidia Nemotron 3 Super 120B: —

  • AIME

    Competition mathematics

    • GPT 4.1: 43.7%
    • Nvidia Nemotron 3 Super 120B: —

  • MATH-500

    Competition math problems

    • GPT 4.1: 91.3%
    • Nvidia Nemotron 3 Super 120B: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT 4.1: 13.6%
    • Nvidia Nemotron 3 Super 120B: 28.8%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT 4.1: 47.1%
    • Nvidia Nemotron 3 Super 120B: 67.8%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 4.1: 68.3%Top
    • Nvidia Nemotron 3 Super 120B: 65.7%

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.

Prompt cache hits
57.9%
About $1.13 per 1M input tokens with caching
Request success (24h)
100.0%
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 100.0%
  • 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": "openai/gpt-4.1",
    "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="openai/gpt-4.1",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.