NOUMENOpen app
NOUMEN

OpenAI · Efficient

GPT 5 Mini

Added Aug 7, 2025

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

A lightweight version of GPT-5 for cost-sensitive applications. Balances advanced capabilities with efficient resource usage.

  • Reasoning
  • Vision
Input
Text, Images
Output
Text
Reasoning effort
minimal · low · medium · high
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.25
Output
$2.00
Cache read
$0.025

Reference prices as published by the model provider. API example

Specifications

Context window
400K
Max output
128K
Average output (7 days)
891 tokens
Longer than 67% of 465 models

Side by side

Compare models

Put GPT 5 Mini next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryGemma 4 26B A4BStep 3.5 Flash 2603DeepSeek V3.2 Exp ThinkingAll 3

Public evaluations

Benchmarks

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

Intelligence Index

16.8

Tested at high reasoning effort

Better than 45% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    15.6

    Composite of the coding evaluations

    Better than 10% of 168 scored models

  • Math Index

    90.7

    Composite of the math evaluations

    Better than 88% of 118 scored models

Agentic work

  • AutomationBench-AA

    6.5%

    Workflow automation, penalized for guardrail violations

    Better than 31% of 173 scored models

  • AutomationBench-AA tasks completed

    0.9%

    Workflows finished end to end without a guardrail violation

    Better than 32% of 173 scored models

  • AA-Briefcasev1.1

    428 Elo

    Agentic knowledge work, rated head to head

    Better than 15% of 166 scored models

  • GDPval-AAv2.1

    766 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 24% of 187 scored models

Document reasoning

  • GDP.pdf

    8.4%

    Professional reasoning over PDF documents, all-pass rate

    Better than 32% of 171 scored models

  • AA-LCRv1.1

    72.3%

    Reasoning across long documents

    Better than 54% of 309 scored models

  • MLCR-AA

    8.9%

    Long-context reasoning over medical records

    Better than 32% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    21.5%

    Expert-level questions across academic fields

    Better than 49% of 323 scored models

  • GPQA Diamond

    82.8%

    Graduate-level science questions

    Better than 53% of 291 scored models

  • MMLU-Pro

    83.7%

    Multi-subject knowledge and reasoning

    Better than 78% of 132 scored models

  • IFBench

    75.4%

    Following precise output instructions

    Better than 84% of 215 scored models

Coding

  • Terminal-Benchv4.0

    0.0%

    Practical software engineering in a terminal

    Better than 0% of 171 scored models

  • SciCode

    39.0%

    Scientific computing in Python

    Better than 19% of 174 scored models

  • LiveCodeBench

    83.8%

    Recent competitive programming problems

    Better than 90% of 129 scored models

Math

  • AIME 2025

    90.7%

    Competition mathematics, 2025 problems

    Better than 88% of 118 scored models

Legacy evaluations

  • Terminal-Bench Hard

    33.3%

    Earlier terminal task suite

    Better than 64% of 212 scored models

  • τ²-Bench Telecom

    68.4%

    Tool use in a customer-support simulation

    Better than 53% of 214 scored models

  • AA-LCR (unversioned)

    72.3%

    Long-context reasoning, earlier grading

    Better than 54% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. GPT 5 Mini was tested at high reasoning effort; compare scores measured at the same effort.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
21.4%
About $0.20 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-5-mini",
    "reasoning_effort": "medium",
    "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-5-mini",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.