NOUMENOpen app
NOUMEN

OpenAI · Efficient

GPT 5 Nano

Added Aug 7, 2025

Compare models

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

Loading models…

Use in the app

Optimized for speed and ideal for applications requiring low latency. The fastest and most efficient GPT-5 variant.

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

Pricing

USD per 1M tokens
Input
$0.05
Output
$0.40
Cache read
$0.005

Reference prices as published by the model provider. API example

Specifications

Context window
400K
Max output
128K
Average output (7 days)
322 tokens
Longer than 35% of 468 models

Side by side

GPT 5 Nano 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 5 NanoOpenAIThis modelGemini 2.5 Flash 0520 ThinkingGoogleRemove
ProviderOpenAIGoogle
Discovery tierEfficientEfficient
AddedAug 7, 2025May 20, 2025
Limits
Context window400K1.05MBest
Max output128KBest65.54K
Average output322 tokens—
Pricing, USD per 1M tokens
Input$0.05Best$0.15
Output$0.40Best$3.50
Cache read$0.005Best$0.015
Performance
Throughput96.6 tok/s—
Time to first token1.8 s—
Request success (24h)99.9%Best99.3%
Benchmark indexes
Intelligence Index13.013.1Best
Math Index83.7Best73.3
Capabilities
ReasoningYesYes
VisionYesYes
Reasoning effortminimal, low, medium, highlow, medium, high

Public evaluations

Benchmarks

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

  • GPT 5 Nano
  • Gemini 2.5 Flash 0520 Thinking

Intelligence Index

  • GPT 5 Nano13.0
  • Gemini 2.5 Flash 0520 Thinking13.1

GPT 5 Nano tested at high reasoning effort

GPT 5 Nano: Better than 31% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • GPT 5 Nano: 83.7Top
    • Gemini 2.5 Flash 0520 Thinking: 73.3

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 5 Nano: 45.0%
    • Gemini 2.5 Flash 0520 Thinking: 65.3%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 5 Nano: 9.5%
    • Gemini 2.5 Flash 0520 Thinking: 12.1%Top

  • GPQA Diamond

    Graduate-level science questions

    • GPT 5 Nano: 67.6%
    • Gemini 2.5 Flash 0520 Thinking: 79.0%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT 5 Nano: 78.0%
    • Gemini 2.5 Flash 0520 Thinking: 83.2%Top

  • IFBench

    Following precise output instructions

    • GPT 5 Nano: 67.6%Top
    • Gemini 2.5 Flash 0520 Thinking: 50.3%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • GPT 5 Nano: 78.9%Top
    • Gemini 2.5 Flash 0520 Thinking: 69.5%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT 5 Nano: 83.7%Top
    • Gemini 2.5 Flash 0520 Thinking: 73.3%

  • AIME

    Competition mathematics

    • GPT 5 Nano: —
    • Gemini 2.5 Flash 0520 Thinking: 82.3%

  • MATH-500

    Competition math problems

    • GPT 5 Nano: —
    • Gemini 2.5 Flash 0520 Thinking: 98.1%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT 5 Nano: 12.1%
    • Gemini 2.5 Flash 0520 Thinking: 13.6%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT 5 Nano: 36.5%Top
    • Gemini 2.5 Flash 0520 Thinking: 31.6%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 5 Nano: 45.0%
    • Gemini 2.5 Flash 0520 Thinking: 65.3%Top

Scores from Artificial Analysis, updated Oct 26, 2026. GPT 5 Nano 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.

Throughput
96.6 tok/s
Faster than 62% of 254 models
Time to first token
1.8 s
Quicker than 86% of 254 models
Prompt cache hits
30.4%
About $0.0363 per 1M input tokens with caching
Request success (24h)
99.9%
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 99.7%
  • 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-nano",
    "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-nano",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.