The Known Good Updated 4 Sep 2026 Subscribe
OpenAI: GPT-5.4 vs OpenAI: GPT-5 Mini ·OpenAI vs OpenAI

OpenAI: GPT-5.4 vs OpenAI: GPT-5 Mini — head-to-head comparison

OpenAI: GPT-5.4 profile OpenAI: GPT-5 Mini profile All comparisons
OpenAI: GPT-5.4 — OpenAI
Quality
#9 of 65
91based on 5 of 7 evaluations
Known Good Index
Speed
#78 of 338
79.6
Output tokens per second
Price
#393 of 442
$5.62
Blended per 1M tokens
In $2.50 · Out $15.00
Cache hit price
#265 of 324
$0.25
per 1M tokens (−90%)
Context
#31 of 476
1.05M
tokens (~1,600 pages)
OpenAI: GPT-5 Mini — OpenAI
Quality
#34 of 65
67based on 6 of 7 evaluations
Known Good Index
Speed
#82 of 338
78.3
Output tokens per second
Price
#190 of 442
$0.69
Blended per 1M tokens
In $0.25 · Out $2.00
Cache hit price
#67 of 324
$0.025
per 1M tokens (−90%)
Context
#185 of 476
400k
tokens (~600 pages)
Summary

On the Known Good Index, OpenAI: GPT-5.4 scores 91 and OpenAI: GPT-5 Mini scores 67 — a 24-point lead for OpenAI: GPT-5.4. They share 5 published evaluations, with OpenAI: GPT-5.4 ahead on 5 and OpenAI: GPT-5 Mini ahead on 0.

Blended pricing is $5.62 per 1M tokens for OpenAI: GPT-5.4 and $0.69 for OpenAI: GPT-5 Mini — OpenAI: GPT-5 Mini is about 8.2× cheaper.

Throughput is 80 tokens per second for OpenAI: GPT-5.4 and 78 for OpenAI: GPT-5 Mini, with time to first token at 1.6s and 4.2s. OpenAI: GPT-5.4 accepts 1.05M tokens of context against 400k.

OpenAI: GPT-5.4 is proprietary; OpenAI: GPT-5 Mini is proprietary. 3 tracked hosts serve one or both, and 2 serve both.

Generated from tracked data on 4 Sep 2026 · how these comparisons are computed →

At a glance
MetricOpenAI: GPT-5.4OpenAI: GPT-5 Mini
Known Good Index 91 based on 5 of 7 evaluations 67 based on 6 of 7 evaluations
Blended $/1M $5.62 $0.69
Output tok/s 80 78
Context window 1.05M 400k
Providers 3 2
Jump to section

Quality

Known Good Index and the capability indices, side by side

Index scores

Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.

MetricOpenAI: GPT-5.4OpenAI: GPT-5 Mini
Known Good Index 91 67
Coding Index 92 51
Mathematics Index — 93
Reasoning Index 87 57
Openness Index 5 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = OpenAI: GPT-5.4 · marker = OpenAI: GPT-5 Mini · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond93 / 75
Mock AIME 2024–2598 / 87
SWE-bench Verified77 / 65
Humanity's Last Exam36 / 19
Terminal-Bench82 / 35

Right-hand figures read OpenAI: GPT-5.4 / OpenAI: GPT-5 Mini. OpenAI: GPT-5.4 leads on 5 of 5, OpenAI: GPT-5 Mini on 0.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena ratings

Elo from blind pairwise votes, ingested from Arena. Higher is better.

MetricOpenAI: GPT-5.4OpenAI: GPT-5 Mini
Text Arena 1,453 —
Text Arena (style controlled) 1,466 —
The Known Good

Price & Cost

Published API pricing by token type

Published pricing

USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.

MetricOpenAI: GPT-5.4OpenAI: GPT-5 Mini
Input $/1M $2.50 $0.25
Output $/1M $15.00 $2.00
Blended $/1M $5.62 $0.69
Cache read $/1M $0.250 $0.025
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input accepted and maximum output emitted

Context and output limits

Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.

MetricOpenAI: GPT-5.4OpenAI: GPT-5 Mini
Context window 1.05M 400k
Max output tokens 128k 128k
The Known Good

Speed & Latency

Mean throughput and time to first token across hosting providers, over successful measurements from the last 48 hours

Throughput and latency

Means across all tracked providers over successful measurements from the last 48 hours, derived from OpenRouter endpoint telemetry.

MetricOpenAI: GPT-5.4OpenAI: GPT-5 Mini
Output tokens/s 80 78
Time to first token 1.6s 4.2s
The Known Good

Providers

Which hosts serve each model, and at what price and speed

3 hosts · 2 serve both
Full provider benchmarks →
Provider OpenAI: GPT-5.4 blendedOpenAI: GPT-5.4 tok/s OpenAI: GPT-5 Mini blendedOpenAI: GPT-5 Mini tok/s
OpenAI · first party $2.81 71 $0.34 75
Azure · first party $5.62 67 $0.69 116
Amazon Bedrock · first party $6.19 — — —

Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.

The Known Good
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →