OpenAI · all models ›

OGPT-5 NanoAPI

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.

400KContext window · tokens
$0.05Input price · per M tokens
$0.4Output price · per M tokens
OpenAIProvider

Prices update automatically — checked daily against provider list prices.

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for GPT-5 Nano, measured by Artificial Analysis. Higher is better. Measurement mode: high.

Intelligence index20.1
Math index83.7
GPQA67.6%
MMLU-Pro78%
Humanity's Last Exam9.5%
Long Context Reasoning43.7%
LiveCodeBench78.9%
SciCode36.6%
AIME 202583.7%
IFBench67.6%
τ²-Bench36.5%
Terminal-Bench Hard12.1%
💰 Blended price$0.138 / 1M tokens
📈 Value145.7 intelligence points per $
vs. models measured heretop 64%
Scores higher than 36% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $0.88 per 1M tokens (median of 24) — this one costs $0.14.
Cheaper and better on this index: GLM 5.3 Flash · DeepSeek V4 Flash 0731 · DeepSeek V4 Flash 0423 and 5 more
Benchmark data by Artificial Analysis

About this model

GPT-5 Nano is a commercial AI model by OpenAI. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is GPT-5 Nano?

GPT-5 Nano is an AI language model from OpenAI. It is a proprietary model, available through an API. It scores 20.1 on the Artificial Analysis intelligence index.

Is GPT-5 Nano free?

GPT-5 Nano is not free: it costs $0.05 per million input tokens and $0.4 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is GPT-5 Nano good at?

Independent benchmarks from Artificial Analysis give it GPQA 67.6%, MMLU-Pro 78%, Humanity's Last Exam 9.5%, Long Context Reasoning 43.7%, LiveCodeBench 78.9%, SciCode 36.6%, AIME 2025 83.7%, IFBench 67.6%, τ²-Bench 36.5%, Terminal-Bench Hard 12.1%. It is particularly used for mathematical reasoning.

Related models

o1-proOpenAIo1-pro (batch)OpenAIGPT-5.5 ProOpenAIGPT-5.4 ProOpenAIGPT-5.2 ProOpenAIGPT-5 ProOpenAI