The Known Good Updated 25 Jul 2026
OpenAI: GPT-5.4 vs OpenAI: GPT-5 Nano ·OpenAI vs OpenAI

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

OpenAI: GPT-5.4 profile OpenAI: GPT-5 Nano profile All comparisons
OpenAI: GPT-5.4 — OpenAI
Quality
#10 of 61
90based on 5 of 6 evaluations
Known Good Index
Speed
#78 of 316
82.3
Output tokens per second
Price
#299 of 340
$5.62
Blended per 1M tokens
In $2.50 · Out $15.00
Cache hit price
#160 of 206
$0.25
per 1M tokens (−90%)
Context
#15 of 345
1.05M
tokens (~1,600 pages)
OpenAI: GPT-5 Nano — OpenAI
Quality
#37 of 61
57based on 3 of 6 evaluations
Known Good Index
Speed
#28 of 316
120.9
Output tokens per second
Price
#56 of 340
$0.14
Blended per 1M tokens
In $0.05 · Out $0.40
Cache hit price
#13 of 206
$0.005
per 1M tokens (−90%)
Context
#105 of 345
400k
tokens (~600 pages)
Summary

On the Known Good Index, OpenAI: GPT-5.4 scores 90 and OpenAI: GPT-5 Nano scores 57 — a 32-point lead for OpenAI: GPT-5.4. They share 3 published evaluations, with OpenAI: GPT-5.4 ahead on 3 and OpenAI: GPT-5 Nano ahead on 0.

Blended pricing is $5.62 per 1M tokens for OpenAI: GPT-5.4 and $0.14 for OpenAI: GPT-5 Nano — OpenAI: GPT-5 Nano is about 40.9× cheaper.

Throughput is 82 tokens per second for OpenAI: GPT-5.4 and 121 for OpenAI: GPT-5 Nano, with time to first token at 2.1s and 2.9s. OpenAI: GPT-5.4 accepts 1.05M tokens of context against 400k.

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

Generated from tracked data on 25 Jul 2026 · how these comparisons are computed →

At a glance
MetricOpenAI: GPT-5.4OpenAI: GPT-5 Nano
Known Good Index 90 based on 5 of 6 evaluations 57 based on 3 of 6 evaluations
Blended $/1M $5.62 $0.14
Output tok/s 82 121
Context window 1.05M 400k
Providers 2 2
Jump to section

Quality

Known Good Index and the capability indices, side by side

IndicesComponents
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 Nano
Known Good Index 90 57
Coding Index 89 —
Mathematics Index 95 89
Science Index 98 69
Reasoning Index 88 —
Agentic Index 89 21
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 Nano · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond93 / 69
MATH / AIME95 / 81
Terminal-Bench82 / 22

Right-hand figures read OpenAI: GPT-5.4 / OpenAI: GPT-5 Nano. OpenAI: GPT-5.4 leads on 3 of 3, OpenAI: GPT-5 Nano 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 Nano
Text Arena 1,453 —
Text Arena (style controlled) 1,466 —
The Known Good

Price & Cost

Published API pricing by token type

Per token typeCache discount
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 Nano
Input $/1M $2.50 $0.05
Output $/1M $15.00 $0.40
Blended $/1M $5.62 $0.14
Cache read $/1M $0.250 $0.005
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 Nano
Context window 1.05M 400k
Max output tokens 128k 128k
The Known Good

Speed & Latency

Median throughput and time to first token across hosting providers

Output speedTime to first token
Throughput and latency

Medians across all tracked providers, derived from OpenRouter endpoint telemetry.

MetricOpenAI: GPT-5.4OpenAI: GPT-5 Nano
Output tokens/s 82 121
Time to first token 2.1s 2.9s
The Known Good

Providers

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

2 hosts · 2 serve both
Full provider benchmarks →
Provider OpenAI: GPT-5.4 blendedOpenAI: GPT-5.4 tok/s OpenAI: GPT-5 Nano blendedOpenAI: GPT-5 Nano tok/s
Azure · first party $5.62 79 $0.14 69
OpenAI · first party $2.81 68 $0.07 225

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 →