OpenAI

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

Input Cost
$0.75/1M
Output Cost
$4.5/1M
Context Window
400K
Max Output
128K
Knowledge Cutoff
Aug 2025
Accepts
text, image

GPT-5.4 mini is an AI model by OpenAI. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.

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

General Benchmarks

AA Intelligence Index
24.635th 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
19.735th of 70

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

Artificial Analysis (via OpenRouter)
GPQA Diamond
83.7%43rd of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
63.0%64th of 93

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

OpenRouter (measured)

Cost Benchmarks

Input Cost
$0.75275th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$4.5305th of 413

Cost per 1M output tokens

OpenRouter API
Cached Input Cost
$0.0754th 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 37 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
Kenari$0$0—400K—
Xpersona$0.375$4$0.0375272K—
Poe$0.68$4$0.068400K—
302.AI$0.75$4.5—400K—
Abacus$0.75$4.5$0.075400K—
AIHubMix$0.75$4.5$0.075400K—
Azure$0.75$4.5$0.075400KSupported
Azure Cognitive Services$0.75$4.5$0.075400K—
Cloudflare AI Gateway$0.75$4.5$0.075128K—
CrossModel$0.75$4.5$0.075400K—
Databricks$0.75$4.5$0.075400K—
DevPass (LLM Gateway)$0.75$4.5$0.075400K—
Eden AI$0.75$4.5$0.075400K—
FastRouter$0.75$4.5—400K—
FreeModel$0.75$4.5$0.075400K—
FrogBot$0.75$4.5$0.075400K—
GitHub Copilot$0.75$4.5$0.075400K—
Impossibl$0.75$4.5$0.075400K—
Kilo Gateway$0.75$4.5$0.075400K—
LLM Gateway$0.75$4.5$0.075400K—
Merge Gateway$0.75$4.5$0.075400K—
NanoGPT$0.75$4.5$0.075400K—
NEAR AI Cloud$0.75$4.5$0.075400K—
Neon$0.75$4.5$0.075400K—
Ofox$0.75$4.5$0.075400K—
OpenAI$0.75$4.5$0.075400KSupported
OpenCode Zen$0.75$4.5$0.075400K—
OpenRouter$0.75$4.5$0.075400KSupported
Opper$0.75$4.5$0.075400K—
OrcaRouter$0.75$4.5$0.075400K—
Pioneer$0.75$4.5$0.075400K—
Requesty$0.75$4.5$0.075400K—
Vercel AI Gateway$0.75$4.5$0.075400KSupported
Vivgrid$0.75$4.5$0.075400K—
ZenMux$0.75$4.5—400K—
Venice AI$0.9375$5.625$0.09375400K—
Model Oracle AI———400K—

GPT-5.4 mini — Benchmark Scores Overview

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

GPT-5.4 mini — Frequently Asked Questions

How much does GPT-5.4 mini cost?

GPT-5.4 mini costs $0.75 per 1M input tokens and $4.5 per 1M output tokens. This is mid-range pricing for its capability level.

What is the context window of GPT-5.4 mini?

GPT-5.4 mini 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 mini?

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

Is GPT-5.4 mini open source?

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