NOUMENOpen app
NOUMEN

OpenAI · Efficient

GPT 4.1 Mini

Added Sep 10, 2025

Compare models

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

Loading models…

Use in the app

Mid-sized GPT 4.1, comparable to GPT4o with a far higher context window, at lower cost and with higher speed.

  • Vision
Input
Text, Images
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.40
Output
$1.60
Cache read
$0.10

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
32.8K
Average output (7 days)
19 tokens
Longer than 0% of 465 models

Side by side

GPT 4.1 Mini 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 4.1 MiniOpenAIThis modelQwen3 VL 235B A22B Instruct OriginalQwenRemove
ProviderOpenAIQwen
Discovery tierEfficientBalanced
AddedSep 10, 2025Sep 25, 2025
Limits
Context window1.05M—
Max output32.77K32.77K
Average output19 tokens288 tokens
Pricing, USD per 1M tokens
Input$0.40$0.30Best
Output$1.60Best$1.90
Cache read$0.10—
Performance
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index10.2Best9.9
Coding Index20.2—
Math Index46.370.7Best
Capabilities
VisionYesYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • GPT 4.1 Mini
  • Qwen3 VL 235B A22B Instruct Original

Intelligence Index

  • GPT 4.1 Mini10.2
  • Qwen3 VL 235B A22B Instruct Original9.9

GPT 4.1 Mini: Better than 22% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT 4.1 Mini: 20.2
    • Qwen3 VL 235B A22B Instruct Original: —

  • Math Index

    Composite of the math evaluations

    • GPT 4.1 Mini: 46.3
    • Qwen3 VL 235B A22B Instruct Original: 70.7Top

Agentic work

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 4.1 Mini: 270 Elo
    • Qwen3 VL 235B A22B Instruct Original: —

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 4.1 Mini: 44.0%Top
    • Qwen3 VL 235B A22B Instruct Original: 32.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 4.1 Mini: 5.0%
    • Qwen3 VL 235B A22B Instruct Original: 6.6%Top

  • GPQA Diamond

    Graduate-level science questions

    • GPT 4.1 Mini: 66.4%
    • Qwen3 VL 235B A22B Instruct Original: 71.2%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT 4.1 Mini: 78.1%
    • Qwen3 VL 235B A22B Instruct Original: 82.3%Top

  • IFBench

    Following precise output instructions

    • GPT 4.1 Mini: 38.3%
    • Qwen3 VL 235B A22B Instruct Original: 42.7%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • GPT 4.1 Mini: 48.3%
    • Qwen3 VL 235B A22B Instruct Original: 59.4%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT 4.1 Mini: 46.3%
    • Qwen3 VL 235B A22B Instruct Original: 70.7%Top

  • AIME

    Competition mathematics

    • GPT 4.1 Mini: 43.0%
    • Qwen3 VL 235B A22B Instruct Original: —

  • MATH-500

    Competition math problems

    • GPT 4.1 Mini: 92.5%
    • Qwen3 VL 235B A22B Instruct Original: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT 4.1 Mini: 7.6%Top
    • Qwen3 VL 235B A22B Instruct Original: 6.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT 4.1 Mini: 52.9%Top
    • Qwen3 VL 235B A22B Instruct Original: 35.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 4.1 Mini: 44.0%Top
    • Qwen3 VL 235B A22B Instruct Original: 32.7%

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
55.9%
About $0.23 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-mini",
    "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-mini",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.