text model comparison

GPT-5.4 vs GPT-6 Luna

GPT-5.4 and GPT-6 Luna are both current text models, from OpenAI. GPT-6 Luna is 96% cheaper per 1M input tokens than GPT-5.4, $0.10 vs $2.50. On Arena Text, GPT-5.4 scores 1475 Elo and GPT-6 Luna 1443 Elo (Arena, measured October 8, 2026). Both accept 1,050,000 tokens of context.

Higher Arena Text: GPT-5.41475 Elo against 1443 Elo
Lower price per 1M input tokens: GPT-6 Luna$0.10 against $2.50
Newer release: GPT-6 LunaSep 2026 against Mar 2026

Data verified October 13, 2026 · Dataset 2026-10-28

GPT-5.4 and GPT-6 Luna, line by line

Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.

Fact	GPT-5.4	GPT-6 Luna
Price
Price per 1M input tokens	$2.50	$0.10 (better)
Price per 1M output tokens	$15	$0.50 (better)
Independent benchmarks
Arena Text	1475 Elo (#21 of 49) (better)	1443 Elo (#37 of 49)
GPQA Diamond	93.3% (#13 of 40) (better)	90.5% (#25 of 40)
FrontierMath Tiers 1-3 (v2)	78.6% (#15 of 40)	78.9% (#14 of 40) (better)
SimpleQA Verified	45.1% (#24 of 36) (better)	41.4% (#26 of 36)
LiveBench Overall	77.97 points (#3 of 5)	Not measured
Specs
Provider	OpenAI	OpenAI
Release date	March 5, 2026	September 22, 2026
Access	API only	API only
Context window	1,050,000 tokens	1,050,000 tokens
Max output	128,000 tokens	128,000 tokens
Input	text, image	text, image
Output	text	text

Scores:Arena · 2026-10-12 Epoch AI · 2026-10-12 LiveBench · 2026-06-25

Open both in the interactive comparison

Charts

Against every current text model

Where GPT-5.4 and GPT-6 Luna land among the current models of their task, on every independent benchmark, on price and on context.

Where each stands

On Arena Text, GPT-5.4 ranks #21 and GPT-6 Luna #37 of 49 current models. Each bar is the share of current models it beats: on score, price and context.

Independent benchmarks

Arena Text

GPT-5.4:#21of 49

1,475 Elo · ahead of 52%

GPT-6 Luna:#37of 49

1,443 Elo · ahead of 23%

GPQA Diamond

GPT-5.4:#13of 40

93.3% · ahead of 67%

GPT-6 Luna:#25of 40

90.5% · ahead of 36%

FrontierMath Tiers 1-3 (v2)

GPT-5.4:#15of 40

78.6% · ahead of 64%

GPT-6 Luna:#14of 40

78.9% · ahead of 67%

SimpleQA Verified

GPT-5.4:#24of 36

45.1% · ahead of 34%

GPT-6 Luna:#26of 36

41.4% · ahead of 29%

LiveBench Overall

GPT-5.4:#3of 5

78 · ahead of 50%

GPT-6 Luna: Not scored

Price and context

Price per 1M input tokens

GPT-5.4:#40of 51

$2.50 · cheaper than 22%

GPT-6 Luna:#1of 51

$0.10 · cheaper than 96%

Price per 1M output tokens

GPT-5.4:#40of 51

$15 · cheaper than 20%

GPT-6 Luna:#3of 51

$0.50 · cheaper than 92%

Context window

GPT-5.4:#1of 66

1.05M tokens · longer than 86%

GPT-6 Luna:#1of 66

1.05M tokens · longer than 86%

Scores fromArena · 2026-10-12 Epoch AI · 2026-10-12 LiveBench · 2026-06-25

Quality against price

Arena Text · measured October 8, 2026

GPT-5.4 scores 1,475 at $5.63; GPT-6 Luna scores 1,443 at $0.2 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.

Quality against price: the data

Arena Text score against price for 41 text models, GPT-5.4 and GPT-6 Luna marked.
Model	Provider	Blended price per 1M tokens	Arena Text (Elo)
Gemini 4 Argon	Google	$4	1,525
Claude Opus 5.5	Anthropic	$8	1,507
Claude Fable 5	Anthropic	$20	1,504
Claude Fable 5.1	Anthropic	$20	1,501
Gemini 3.8 Flash	Google	$1.50	1,497
Muse Spark 1.3	Meta	$2	1,494
Claude Opus 5	Anthropic	$10	1,490
Kimi K3	Moonshot Kimi	$6	1,488
Gemini 3.7 Flash	Google	$1.50	1,486
GPT-5.6 Sol	OpenAI	$8	1,485
GPT-6.1 Sol	OpenAI	$4	1,484
Qwen3.8-Max	Alibaba Qwen	$3	1,483
GPT-5.5	OpenAI	$11	1,482
Gemini 3.6 Flash	Google	$3	1,482
Claude Opus 4.8	Anthropic	$10	1,481
MiMo-V2.6-Pro	Xiaomi MiMo	$0.54	1,480
GLM-5.3	Z.ai	$2.15	1,478
Claude Sonnet 5.5	Anthropic	$4	1,476
GPT-5.4	OpenAI	$5.63	1,475
GPT-6 Astra	OpenAI	$20	1,475
DeepSeek-V4.1-Flash	DeepSeek	$0.52	1,475
GLM-5.3-Flash	Z.ai	$0.24	1,475
Gemini 3 Flash Preview	Google	$1.13	1,473
Grok 4.20	xAI	$1.56	1,472
GPT-5.6 Terra	OpenAI	$4.50	1,466
Grok 4.5	xAI	$3	1,466
DeepSeek-V4-Pro	DeepSeek	$1.98	1,465
Claude Sonnet 5	Anthropic	$4	1,461
GPT-6 Sol	OpenAI	$4	1,456
Gemini 3.5 Flash-Lite	Google	$0.85	1,455
Grok 4.6	xAI	$3	1,454
GPT-5.6 Luna	OpenAI	$0.45	1,452
MiMo-V2.6-Flash	Xiaomi MiMo	$0.18	1,451
GPT-6 Luna	OpenAI	$0.20	1,443
Grok 4.7	xAI	$3	1,443
Grok 4.3	xAI	$1.56	1,442
Mistral Large 4	Mistral AI	$2.06	1,429
GPT-4.1	OpenAI	$3.50	1,415
Solar Pro 4	Upstage	$0.52	1,386
GPT-4.1 mini	OpenAI	$0.70	1,383
GPT-4.1 nano	OpenAI	$0.18	1,322

Cost

What each costs

Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.

The same work, priced

For 10M input and 2M output tokens, GPT-5.4 costs 28 times as much as GPT-6 Luna, at each provider's listed rates.

10M input and 2M output tokens
GPT-5.4 costs 28× as much
GPT-5.4
$55
GPT-6 Luna
$2
The same, with 9M of the input tokens cached
GPT-5.4 costs 29× as much
GPT-5.4
$34.75
GPT-6 Luna
$1.19

Workload or rate	GPT-5.4	GPT-6 Luna
Example workloads
10M input and 2M output tokens	$55	$2 (better)
The same, with 9M of the input tokens cached	$34.75	$1.19 (better)
Other listed rates
1M input tokens, cached	$0.25	$0.01 (better)
1M input tokens, prompts over 272K tokens	Not listed	$0.20
1M output tokens, prompts over 272K tokens	Not listed	$0.75

Verdict

When to choose each

GPT-5.4

Where it leads

Higher Arena Text score, 1475 Elo vs 1443 Elo
Higher GPQA Diamond score, 93.3% vs 90.5%
Higher SimpleQA Verified score, 45.1% vs 41.4%

Best for

Long-context coding and professional-work evaluations

Watch out for

Prompts above the provider long-context threshold use higher token rates; reproduce cost and quality on the target workload

Full GPT-5.4 profile

GPT-6 Luna

Where it leads

Lower input and output prices, $0.10 and $0.50 vs $2.50 and $15 per 1M tokens
Higher FrontierMath Tiers 1-3 (v2) score, 78.9% vs 78.6%
Cheaper cached input, $0.01 vs $0.25 per 1M tokens

Best for

High-volume summarisation, extraction and routing
Long-context budget work, where the 272k threshold is more forgiving than Haiku 5.5's 100k

Watch out for

Prompts over 272,000 tokens are rebilled at $0.20 input and $0.75 output for the whole request
A twentieth of GPT-6 Sol's price reflects a capability gap, not a discount on the same model

Full GPT-6 Luna profile

From benchmark to production

Building on GPT-5.4 or GPT-6 Luna?

Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.

Book a consultation AI agent development

FAQ

GPT-5.4 vs GPT-6 Luna FAQ

Which is cheaper, GPT-5.4 or GPT-6 Luna?

GPT-6 Luna is 96% cheaper per 1M input tokens than GPT-5.4, $0.10 vs $2.50. For 10M input and 2M output tokens, GPT-5.4 costs $55 and GPT-6 Luna $2 at standard rates.

Which is cheaper with prompt caching, GPT-5.4 or GPT-6 Luna?

GPT-5.4 charges $0.25 per 1M cached input tokens, 90% below its standard input rate, and GPT-6 Luna $0.01, 90% below. With 9M of 10M input tokens cached and 2M output tokens, GPT-5.4 costs $34.75 and GPT-6 Luna $1.19.

Which scores higher on independent benchmarks, GPT-5.4 or GPT-6 Luna?

GPT-5.4 leads on Arena Text, 1475 Elo to 1443 Elo; GPT-5.4 leads on GPQA Diamond, 93.3% to 90.5%; GPT-6 Luna leads on FrontierMath Tiers 1-3 (v2), 78.9% to 78.6%. Scores are independent evaluations, not either vendor's launch figures.

Which has the larger context window, GPT-5.4 or GPT-6 Luna?

Both accept 1,050,000 tokens of context. Both return up to 128,000 tokens per response.

Choosing between GPT-5.4 and GPT-6 Luna?

Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

A head-to-head evaluation on your real workload
Routing between models by cost and difficulty

Compare all models Book a consultation