modelgrep
openai logo

OpenAI: GPT-5 Nano

openai/gpt-5-nano

122nd smartest of 182Cheaper than 95% of paidReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
19.9
122nd of 182
Design Elo
1125
Website
Speed
tokens/sec
Latency
first token
Input price
$0.050
16th cheapest
Context
400K
128K max out

How it compares

Smarter than33%
of all ranked models
Cheaper than95%
of all ranked models

Overview

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. While limited in reasoning depth compared to its larger...

Benchmarks

independent · Artificial Analysis & Design Arena
Artificial Analysis60th percentile
Intelligence Index
19.9
GPQA Diamond
68%
Humanity's Last Exam
8%
SciCode
37%
Tau²-Bench (agentic)
37%
Design Arena · Elo5,414 tournaments
Website
1125
Data Viz
1089
3D
1021

Providers & pricing (4)

ProviderIn $/MOut $/MUptime
OpenAIcache$0.050$0.40099.3%
OpenAIcache$0.025$0.20099.3%
Azure$0.050$0.40099.9%
Azure$0.055$0.440

Specifications

Context window400K
Max output128K
Knowledge cutoffMay 2024
Input modalitiestext, image, file
Output modalitiestext
Prompt cachingSupported
Cache read price$0.0050/M
ModeratedYes

GPT-5 Nano FAQ

How much does GPT-5 Nano cost?

GPT-5 Nano costs $0.050 per million input tokens and $0.400 per million output tokens via OpenRouter, making it 16th cheapest of 332 paid models.

How smart is GPT-5 Nano?

GPT-5 Nano scores 19.9 on the Artificial Analysis Intelligence Index, ranking 122nd of 182 benchmarked models, with a GPQA Diamond score of 68%.

What is GPT-5 Nano's context window?

GPT-5 Nano supports a 400K-token context window and can output up to 128K tokens. It accepts text, image, file input.

Compare head-to-head