OpenAI

GPT-5.4 nano — Benchmark Scores, Pricing & Performance Analysis

BUDGETOpenAI
Input Cost
$0.20/1M
Output Cost
$1.3/1M
Context Window
400K
Max Output
128K
Knowledge Cutoff
Aug 2025
Accepts
text, image

GPT-5.4 nano by OpenAI demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

General Benchmarks

AA Intelligence Index
21.239th of 66

Artificial Analysis composite intelligence score across 10 sub-benchmarks

Artificial Analysis (via OpenRouter)

Coding Benchmarks

AA Coding Index
56.134th of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)

Reasoning Benchmarks

AA Agentic Index
17.737th of 70

Artificial Analysis composite score for multi-step tool-using tasks

Artificial Analysis (via OpenRouter)
τ²-Bench Airline
67.0%59th of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)
GPQA Diamond
77.9%72nd of 140

Graduate-level science Q&A by domain experts

Papers

Cost Benchmarks

Input Cost
$0.20169th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$1.3215th of 413

Cost per 1M output tokens

OpenRouter API
Cached Input Cost
$0.0216th of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API

Context Benchmarks

Context Length
400K90th of 451

Maximum context window size

OpenRouter API

Available from 32 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 4 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Poe$0.18$1.1$0.018400K
302.AI$0.2$1.25400K
Abacus$0.2$1.25$0.02400K
Azure$0.2$1.25$0.02400KSupported
Azure Cognitive Services$0.2$1.25$0.02400K
Cloudflare AI Gateway$0.2$1.25$0.02128K
CrossModel$0.2$1.25$0.02400K
Databricks$0.2$1.25$0.02400K
DevPass (LLM Gateway)$0.2$1.25$0.02400K
Eden AI$0.2$1.25$0.02400K
FastRouter$0.2$1.25400K
FrogBot$0.2$1.25$0.02400K
GitHub Copilot$0.2$1.25$0.02400K
Impossibl$0.2$1.25$0.02400K
Kilo Gateway$0.2$1.25$0.02400K
LLM Gateway$0.2$1.25$0.02400K
Merge Gateway$0.2$1.25$0.02400K
NanoGPT$0.2$1.25$0.02400K
NEAR AI Cloud$0.2$1.25$0.02400K
Neon$0.2$1.25$0.02400K
Ofox$0.2$1.25$0.02400K
OpenAI$0.2$1.25$0.02400KSupported
OpenCode Zen$0.2$1.25$0.02400K
OpenRouter$0.2$1.25$0.02400KSupported
Opper$0.2$1.25$0.02400K
OrcaRouter$0.2$1.25$0.02400K
Pioneer$0.2$1.25$0.021.0M
Requesty$0.2$1.25$0.02400K
Vercel AI Gateway$0.2$1.25$0.02400KSupported
Vivgrid$0.2$1.25$0.02400K
ZenMux$0.2$1.25400K
Model Oracle AI400K

GPT-5.4 nano — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

GPT-5.4 nano — Frequently Asked Questions

How much does GPT-5.4 nano cost?

GPT-5.4 nano costs $0.20 per 1M input tokens and $1.3 per 1M output tokens. This makes it one of the more affordable models.

What is the context window of GPT-5.4 nano?

GPT-5.4 nano has a context window of 400K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created GPT-5.4 nano?

GPT-5.4 nano was created by OpenAI. It is classified as a budget model in our catalogue.

Is GPT-5.4 nano open source?

No, GPT-5.4 nano is a proprietary model. It is available through OpenAI's API and compatible providers.