Skip to content
LLMs
OpenAI logo

OpenAI: GPT-5.4 Nano

by OpenAI

OpenAI: GPT-5.4 Nano is a large language model from OpenAI. It costs $0.200 per million input tokens and $1.25 per million output tokens. Its context window is 400K tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierfile inputimage input
Input / 1M tokens
$0.200
Output / 1M tokens
$1.25
Cached input / 1M
$0.020

On repeated prefixes

Context window
400K

tokens

This model also charges $0.01 per search request

That is $10.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.0008, so the search fee is 12× the token cost. Per-token rankings elsewhere ignore this entirely.

Who serves it cheapest

2 hosts serve GPT-5.4 Nano. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: GPT-5.4 Nano, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
OpenAICheapest$0.100$0.625400K-100.0%
Azure$0.200$1.25400K-100.0%

The spread between OpenAI and Azure is 2.0× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
21.2
Coding index
56.1
Agentic index
17.7

About GPT-5.4 Nano

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...

Specifications

OpenAI: GPT-5.4 Nano specifications
Model IDopenai/gpt-5.4-nano
ProviderOpenAI
Context window400K tokens
Max output128K tokens
Input modalitiesfile, image, text
Output modalitiestext
Knowledge cutoff2025-08-31
Open weightsNo
ReleasedMarch 17, 2026

Cheaper alternatives

Models that cost less than GPT-5.4 Nano while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does OpenAI: GPT-5.4 Nano cost?

$0.200 per million input tokens and $1.25 per million output tokens. Cached input reads cost $0.020 per million tokens.

What is the context window of OpenAI: GPT-5.4 Nano?

400K tokens, with up to 128K tokens of output per request.

Does OpenAI: GPT-5.4 Nano have extra fees beyond per-token pricing?

Yes. OpenAI: GPT-5.4 Nano charges $0.01 per search request - $10.00 per 1,000 requests - on top of $0.200 per million input tokens and $1.25 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 12× the token cost.

Which provider serves OpenAI: GPT-5.4 Nano cheapest?

OpenAI at $0.100 per million input tokens - 2.0× cheaper than Azure, the most expensive of the 2 hosts serving it.

Confirm against the source: OpenAI official pricing.