modelgrep
O

OpenAI: GPT-5.4 Nano

openai/gpt-5.4-nano

25th smartest of 178ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
44.0
25th of 178
Design Elo
Speed
60
138th fastest
Latency
552ms
first token
Input price
$0.200
95th cheapest
Context
400K
128K max out

How it compares

Smarter than86%
of all ranked models
Faster than53%
of all ranked models
Cheaper than68%
of all ranked models

Overview

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

Benchmarks

independent · via OpenRouter
Artificial Analysis82th percentile
Intelligence Index
44.0
Coding Index
43.9
Agentic Index
47.6
GPQA Diamond
82%
Humanity's Last Exam
27%
SciCode
47%
Tau²-Bench (agentic)
76%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Azure$0.200$1.25100%
OpenAI$0.200$1.2587.6%

Specifications

Context window400K
Max output128K
Knowledge cutoffAug 2025
Input modalitiesfile, image, text
Output modalitiestext
Prompt caching
Cache read price$0.020/M
ModeratedNo

GPT-5.4 Nano FAQ

How much does GPT-5.4 Nano cost?

GPT-5.4 Nano costs $0.200 per million input tokens and $1.25 per million output tokens via OpenRouter, making it 95th cheapest of 298 paid models.

How smart is GPT-5.4 Nano?

GPT-5.4 Nano scores 44.0 on the Artificial Analysis Intelligence Index, ranking 25th of 178 benchmarked models, with a GPQA Diamond score of 82%.

How fast is GPT-5.4 Nano?

GPT-5.4 Nano generates around 60 tokens per second with 552ms time-to-first-token (p50), the 138th fastest tracked model.

What is GPT-5.4 Nano's context window?

GPT-5.4 Nano supports a 400K-token context window and can output up to 128K tokens. It accepts file, image, text input.

Compare head-to-head