GPT-5.4 Mini

Name: GPT-5.4 Mini
Brand: OpenAI
Availability: InStock

openai/gpt-5.4-mini

fast, cost-effective model for everyday tasks.

cmd --model gpt-5.4-mini

Intelligence index

Output speed

183.8 tok/s

Input

$0.75 /M

Output

$4.50 /M

Cache read

$0.07 /M

Agent-loop cost

$0.28 /M in

Context window

400K tokens

Released

March 17, 2026

Modalities

→

vs. the lineup

GPT-5.4 Mini beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:

Model	Intelligence	Coding	Speed	Input $/M	Output $/M	Blended $/M	Context
GPT-5.6 Sol	58.9◆	77.4◆	64.8◆	$5◆	$30◆	$11.25◆	1.05M◆
GPT-5.6 Terra	55◆	76.7◆	122.3◆	$2.50◆	$15◆	$5.63◆	1.05M◆
GPT-5.5	54.8◆	74.9◆	92.4◆	$5◆	$30◆	$11.25◆	200K◆
GPT-5.4	51.4◆	71.1◆	136.5◆	$2.50◆	$15◆	$5.63◆	400K◆
GPT-5.6 Luna	51.2◆	71.4◆	184.4◆	$1◆	$6◆	$2.25◆	1.05M◆
GPT-5.4 Mini ◆	40◆	56.1◆	183.8◆	$0.75◆	$4.50◆	$1.69◆	400K◆
DeepSeek V4 Propinned	44.3◆	59.4◆	70.9◆	$0.43◆	$0.87◆	$0.54◆	1M◆
DeepSeek V4 Flashpinned	40.3◆	56.2◆	122◆	$0.14◆	$0.28◆	$0.18◆	1M◆

Compare all 50 models →

coding performance

The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for GPT-5.4 Mini has been left empty.

Coding Index

56.1

#25 of 34 scored

Terminal-Bench

59.2

#28 of 34 scored

Intelligence Index

#28 of 40 scored

Long-context reasoning

69.3

reasoning across a long context

SciCode

49.9

scientific coding

GPQA Diamond

87.5

graduate-level QA

usage calculator

How far a month of credits goes on GPT-5.4 Mini.

Input tokensfresh prompt

800

Output tokensmodel reply

180

Cache read tokensre-read context

50K

cost / request $0.0052 · in $0.75 · out $4.50 · cache $0.07 per M

fresh input 12%output 16%cache reads 73%

Requests / 30 days

2.9K

$15 credits ÷ $0.0052 per request

~581 quick fixes~116 bug fixes~19 feature PRs

what real work costs

Real coding tasks priced end to end on GPT-5.4 Mini, from a quick lookup to a full-repo agent run.

One agent task

$0.10

180K in at 75% cache hit, 12K out

What you pay

$0.51 /M

all-in across every token that task touched

Sticker input

$0.75 /M

cache reads bill at $0.07 /M instead

Task	Tokens in · out	GPT-5.4 Mini	MiniMax M3	Claude Haiku 4.5
Quick lookup / one-liner	8K · 1K	$0.0056	$0.0019	$0.0065
Review a 500-line PR	60K · 4K	$0.03	$0.01	$0.04
Fix a bug (agent loop)	180K · 12K	$0.10	$0.04	$0.12
Refactor a module	320K · 20K	$0.17	$0.06	$0.21
Full-repo agent run	900K · 45K	$0.40	$0.16	$0.49

frequently asked

What is GPT-5.4 Mini best for?+

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments. The model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.

How much does GPT-5.4 Mini cost?+

$0.75/M input and $4.50/M output, cache reads $0.07/M. In an agent loop most input is cache-read, so the effective input rate is about $0.28/M.

Which plan do I need?+

Available on Pro and above.

How do I switch to it?+

Run cmd --model gpt-5.4-mini, or type /model in a session and pick it. You can switch mid-session without losing context.

GPT-5.6 Sol→

frontier model for complex professional work · $5/$30 per M

GPT-5.6 Terra→

balances intelligence and cost · $2.50/$15 per M

All supported models→

sortable by score, speed and price