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 modelGPT LatestOpenAIRemove
ProviderOpenAIOpenAI
Discovery tierFrontierFrontier
AddedSep 10, 2025Mar 29, 2026
Limits
Context window1.05M1.05MBest
Max output32.77K128KBest
Average output29 tokens311 tokens
Pricing, USD per 1M tokens
Input$2.00Best$10.00
Output$8.00Best$50.00
Cache read$0.50Best$1.00
Cache write—$12.50
Performance
Throughput—171.0 tok/s
Time to first token—22.9 s
Request success (24h)100.0%Best97.7%
Benchmark indexes
Intelligence Index12.749.6Best
Coding Index—76.7
Math Index34.7—
Capabilities
ReasoningNoYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effort—low, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • GPT 4.1
  • GPT Latest

Intelligence Index

  • GPT 4.112.7
  • GPT Latest49.6

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: —
    • GPT Latest: 76.7

  • Math Index

    Composite of the math evaluations

    • GPT 4.1: 34.7
    • GPT Latest: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT 4.1: —
    • GPT Latest: 64.6%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT 4.1: —
    • GPT Latest: 33.6%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT 4.1: —
    • GPT Latest: 1,460 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 4.1: —
    • GPT Latest: 1,487 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT 4.1: —
    • GPT Latest: 30.4%

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 4.1: 68.3%
    • GPT Latest: 79.7%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT 4.1: —
    • GPT Latest: 38.3%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 4.1: 4.2%
    • GPT Latest: 52.7%Top

  • GPQA Diamond

    Graduate-level science questions

    • GPT 4.1: 66.6%
    • GPT Latest: 93.9%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT 4.1: 80.6%
    • GPT Latest: —

  • IFBench

    Following precise output instructions

    • GPT 4.1: 43.0%
    • GPT Latest: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT 4.1: —
    • GPT Latest: 49.5%

  • SciCode

    Scientific computing in Python

    • GPT 4.1: —
    • GPT Latest: 54.2%

  • LiveCodeBench

    Recent competitive programming problems

    • GPT 4.1: 45.7%
    • GPT Latest: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT 4.1: 34.7%
    • GPT Latest: —

  • AIME

    Competition mathematics

    • GPT 4.1: 43.7%
    • GPT Latest: —

  • MATH-500

    Competition math problems

    • GPT 4.1: 91.3%
    • GPT Latest: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT 4.1: 13.6%
    • GPT Latest: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT 4.1: 47.1%
    • GPT Latest: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 4.1: 68.3%
    • GPT Latest: 79.7%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
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.