modelgrep
O

OpenAI: GPT-4.1 Nano

openai/gpt-4.1-nano

155th smartest of 178Cheaper than 80% of paidToolsJSONVision
Use via OpenRouter ↗
Intelligence
13.0
155th of 178
Design Elo
1039
Game Dev
Speed
91
78th fastest
Latency
649ms
first token
Input price
$0.100
59th cheapest
Context
1.0M
33K max out

How it compares

Smarter than13%
of all ranked models
Faster than74%
of all ranked models
Cheaper than80%
of all ranked models

Overview

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Benchmarks

independent · via OpenRouter
Artificial Analysis14th percentile
Intelligence Index
13.0
Coding Index
11.2
Agentic Index
5.8
GPQA Diamond
51%
Humanity's Last Exam
4%
SciCode
26%
Tau²-Bench (agentic)
17%
Design Arena · Elo862 tournaments
Game Dev
1039
Website
1018
codecategories
1015
3D
1005
UI Component
973
Data Viz
935

Providers & pricing (3)

ProviderIn $/MOut $/MUptime
OpenAI$0.100$0.40094.6%
Azurecache$0.100$0.400
Azurecache$0.100$0.400100%

Specifications

Context window1.0M
Max output33K
Knowledge cutoffJun 2024
Input modalitiesimage, text, file
Output modalitiestext
Prompt cachingSupported
Cache read price$0.025/M
ModeratedYes

GPT-4.1 Nano FAQ

How much does GPT-4.1 Nano cost?

GPT-4.1 Nano costs $0.100 per million input tokens and $0.400 per million output tokens via OpenRouter, making it 59th cheapest of 298 paid models.

How smart is GPT-4.1 Nano?

GPT-4.1 Nano scores 13.0 on the Artificial Analysis Intelligence Index, ranking 155th of 178 benchmarked models, with a GPQA Diamond score of 51%.

How fast is GPT-4.1 Nano?

GPT-4.1 Nano generates around 91 tokens per second with 649ms time-to-first-token (p50), the 78th fastest tracked model.

What is GPT-4.1 Nano's context window?

GPT-4.1 Nano supports a 1.0M-token context window and can output up to 33K tokens. It accepts image, text, file input.

Compare head-to-head