GPT-5.4 Mini

openai/gpt-5.4-mini

fast, cost-effective model for everyday tasks.

cmd --model gpt-5.4-mini
Intelligence index
31.9
Output speed
not yet scored
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:
ModelIntelligenceCodingSpeedInput $/MOutput $/MBlended $/MContext
GPT-6 Astra54.776.963.4$10$50$201.05M
GPT-5.6 Sol51.377.473.4$5$30$11.251.05M
GPT-5.6 Terra46.876.7121.2$2$12$4.501.05M
GPT-5.545.674.9$5$30$11.25400K
GPT-5.6 Luna43.471.4116.7$0.20$1.20$0.451.05M
GPT-5.4 Mini31.956.1$0.75$4.50$1.69400K
DeepSeek V4 Pro (latest)pinned42.168.862.1$0.66$1.98$0.991M
DeepSeek V4 Flash (latest)pinned4169.1117.7$0.15$0.60$0.261M

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
#41 of 53 scored
Terminal-Bench
59.2
#44 of 53 scored
Intelligence Index
31.9
#47 of 59 scored
Long-context reasoning
77
reasoning across a long context
GPQA Diamond
87.5
graduate-level QA

usage calculator

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

GPT-5.4 Mini runs on Pro and up — from $20/mo.
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
3.9K
$20 credits ÷ $0.0052 per request
~775 quick fixes~155 bug fixes~26 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
TaskTokens in · outGPT-5.4 MiniMuse Spark 1.3 ContributorClaude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.0056$0.0003$0.0065
Review a 500-line PR60K · 4K$0.03$0.0027$0.04
Fix a bug (agent loop)180K · 12K$0.10$0.0072$0.12
Refactor a module320K · 20K$0.17$0.01$0.21
Full-repo agent run900K · 45K$0.40$0.03$0.49

frequently asked

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.

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.

Benchmarks from Artificial Analysis (v4.3)commandcode.ai/models/gpt-5-4-mini