How much does GPT-5.4 nano cost?

GPT-5.4 nano costs $0.20 per million input tokens and $1.25 per million output tokens on standard pricing; other tiers (Standard, Batch, Flex) are also available. A workload of 20M input and 5M output tokens a month is about $10.

What is the context length of GPT-5.4 nano?

GPT-5.4 nano accepts up to 400,000 tokens (400K) of input and can return up to 128,000 tokens in one response.

Does GPT-5.4 nano support tool calling and structured outputs?

Yes, GPT-5.4 nano supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Reasoning, Deterministic seed, Prompt caching.

What inputs and outputs does GPT-5.4 nano support?

GPT-5.4 nano accepts PDF, Image, Text as input and produces Text as output.

Which providers serve GPT-5.4 nano?

GPT-5.4 nano is available from 4 API providers: OpenAI, Azure, OpenAI, Azure. Prices can differ by provider.

When was GPT-5.4 nano released?

GPT-5.4 nano was released by OpenAI in 2026.

GPT-5.4 nano

gpt-5.4-nano

API Provider site

Smallest GPT-5.4 model for classification, routing and simple extraction at scale. Built by OpenAI.

Prices updated recently

Input price

$0.20

per 1M tokens · Standard

Output price

$1.25

per 1M tokens · Standard

Input limit

400K

tokens

Output limit

128K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF

Compare

GPT-5.4 nano price history

2 price records since 9/25/2026

GPT-5.4 nano cost calculator

Input20M tokens

Output5M tokens

$10/month

Standard pricing

Overview

What is GPT-5.4 nano?

GPT-5.4 nano is a text & reasoning and vision model from OpenAI. Smallest GPT-5.4 model for classification, routing and simple extraction at scale. Its 400K context window and $0.20 input price make it a candidate for cost-sensitive, high-throughput applications.

Image understandingDocument analysisContent workflowsClassification

Benchmarks

GPT-5.4 nano benchmarks & speed

How GPT-5.4 nano scores on standardized evaluations, and where it lands among every model we track.

20.7

Intelligence Index

Better than 51% of 153 models

172tok/s

Output speed

Better than 82% of 119 models

Reasoning

GPQA Diamond

81.7%

Graduate-level scientific reasoning · top 51%

HLE

28.3%

Humanity's Last Exam · top 39%

Coding

SciCode

47.2%

Python for scientific computing · top 60%

Latency & design

Time to first token: 69.77s

Independent scores from Artificial Analysis and DesignArena · updated 10/5/2026. Higher is better; ranks compare against every model we track with that score.

Rates

GPT-5.4 nano pricing

Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

Input · Standard

$0.20

Per 1M tokens

Cached input · Standard

$0.02

Per 1M tokens

Capabilities

GPT-5.4 nano Tools

Tools available when using GPT-5.4 nano through supported provider APIs.

Function calling

Supported

Structured outputs

Supported

JSON mode

Supported

Reasoning

Supported

Built-in web search

Not supported

Log probabilities

Not supported

Deterministic seed

Supported

Parallel tool calls

Not supported

Prompt caching

Supported

Where to run it

GPT-5.4 nano API providers

4 providers serve GPT-5.4 nano. Prices are per 1M tokens; uptime is the last 24 hours.

Provider	Input	Output	Cached	Context	Uptime
OpenAI	$0.10	$0.63	$0.01	400K	100%
Azure	$0.20	$1.25	$0.02	400K	99.98%
OpenAI	$0.20	$1.25	$0.02	400K	99.98%
Azure	$0.22	$1.38	$0.02	400K	—

OpenAI

Input: $0.10
Output: $0.63
Cached: $0.01
Context: 400K
Uptime: 100%

Azure

Input: $0.20
Output: $1.25
Cached: $0.02
Context: 400K
Uptime: 99.98%

OpenAI

Input: $0.20
Output: $1.25
Cached: $0.02
Context: 400K
Uptime: 99.98%

Azure

Input: $0.22
Output: $1.38
Cached: $0.02
Context: 400K
Uptime: —

Strengths and limitations

Strengths

Low input cost at $0.20 per million tokens suits high-volume workloads.
400K context supports large documents, repositories and extended conversations.
Supports text & reasoning and vision workloads in one model.

Limitations

Generated tokens cost 6× more than input tokens, which matters for verbose responses.
Large context capacity does not guarantee consistent retrieval across the entire prompt.
Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

Same provider