Updated 9 Nov · updated in the last 30 hours

Comparison · OpenAI

GPT-5.4 Mini vs GPT-5.4 Nano

Listed API prices of GPT-5.4 Mini and GPT-5.4 Nano turned into the cost of the same three standard tasks. Output quality, speed and answer length are not compared.

Calculated impact cost per task and per month

For an L2 task (deep analysis over a 50,000-token document, 3 steps), GPT-5.4 Mini costs $0.133 and GPT-5.4 Nano $0.036 at the prices listed in the United States on , so GPT-5.4 Mini is 273.4 % more than GPT-5.4 Nano, counting visible output only, without cache discounts or hidden reasoning.

Head to head: GPT-5.4 Mini: $0.133; GPT-5.4 Nano: $0.036 Calculated from published rates Input and visible output are priced separately for the same task. 159,000 input + 3,000 visible output tokens per task. No cache discount; hidden reasoning excluded.
Head to head.Calculated from published rates Input and visible output are priced separately for the same task. 159,000 input + 3,000 visible output tokens per task. No cache discount; hidden reasoning excluded. Open image · Explore the chart · Measured Lab · CC BY 4.0
Compare visually
TaskGPT-5.4 Mini, per taskGPT-5.4 Nano, per taskGPT-5.4 Mini, per monthGPT-5.4 Nano, per monthGPT-5.4 Mini vs GPT-5.4 Nano, per task
L1Micro-task (classification or strict JSON extraction)$0.0020per L1 task$0.0006per L1 task$29.57per month$8.03per month+268.2 %
L2Deep analysis over a 50,000-token document$0.133per L2 task$0.036per L2 task$1,938.15per month$519.03per month+273.4 %
L3Agentic coding loop, 15 steps$1.03per L3 task$0.274per L3 task$14,996.02per month$4,005.51per month+274.4 %

Calculated Per month: 20 tasks an hour around the clock, 730 hours.

GPT-5.4 Mini in the calculatoryour own task shape GPT-5.4 Nano in the calculatoryour own task shape GPT-5.4 Mini model card GPT-5.4 Nano model card

Prices USD per 1M tokens

PriceGPT-5.4 MiniGPT-5.4 Nano
Input, per 1M tokens$0.750$0.200
Output, per 1M tokens$4.50$1.25
Price fromProvider's price list · source page PublishedOpenRouter · source page (data) Published
Read · the United States · the United States
Context window400,000 tokens400,000 tokens

What can I use it for? six common tasks, our data checks

Quality on your task: not measured by Measured Lab yet.

TaskGPT-5.4 MiniGPT-5.4 Nano
Answer customer messagesFits on price and context—
Pull data from invoices and documents with strict JSON and page imagesFits on price and context—
Summarize documents and meetingsFits on price and context—
Translate contentFits on price and context—
Chat assistant on your websiteFits on price and context—
Write and review code with tool callsFits on price and context—
Tasks it fits6 of 6—

Checks of our data for six common tasks: a published price, a context window and answer length for the task and, where the task needs them, strict JSON output, page images and tool calls; prices, cost a month and terms for each model on its model card. GPT-5.4 Nano is not in the model picker. Compare models for your own task in the model picker.

All model comparisons · How we check prices

Explore the numbers

Calculated from published rates

The same work. Two bills.

Input and visible output are priced separately for the same task.

$0.097L2 task differenceGPT-5.4 Nano less
$1,419.12L2 monthly differenceAssumption: 20 tasks/hour × 730 hours
GPT-5.4 Mini$0.133GPT-5.4 Nano$0.036$0.00$0.05$0.10$0.15GPT-5.4 Mini$0.133GPT-5.4 Nano$0.036$0.00$0.05$0.10$0.15
Fresh inputVisible output

159,000 input + 3,000 visible output tokens per task. No cache discount; hidden reasoning excluded.

GPT-5.4 Nano costs $0.097 less per task.

GPT-5.4 Mini$0.0020GPT-5.4 Nano$0.0006$0.00$0.001$0.002$0.003GPT-5.4 Mini$0.0020GPT-5.4 Nano$0.0006$0.00$0.001$0.002$0.003
Fresh inputVisible output

1,500 input + 200 visible output tokens per task. No cache discount; hidden reasoning excluded.

GPT-5.4 Nano costs $0.0015 less per task.

GPT-5.4 Mini$1.03GPT-5.4 Nano$0.274$0.00$0.50$1.00$1.50GPT-5.4 Mini$1.03GPT-5.4 Nano$0.274$0.00$0.50$1.00$1.50
Fresh inputVisible output

1,315,500 input + 9,000 visible output tokens per task. No cache discount; hidden reasoning excluded.

GPT-5.4 Nano costs $0.753 less per task.

GPT-5.4 Mini$1,938.15GPT-5.4 Nano$519.03$0$500$1,000$1,500$2,000GPT-5.4 Mini$1,938.15GPT-5.4 Nano$519.03$0$500$1,000$1,500$2,000
Fresh inputVisible output

Assumption: 20 tasks/hour × 730 hours = 14,600 tasks/month.

Observed · United States

Wait and streaming speed

The same short request. Each route must have successful answers on at least two dates.

GPT-5.4 Mini

Direct API · OpenAI · 120 answers on 23 dates.

First answer token 663 ms
Observed range · dot = median0.010.020.030.040.0secondsObserved range · dot = median0.010.020.030.040.0seconds

GPT-5.4 Mini · 663 ms median; observed range 319 ms–30.57 s.

Output speed 156 tokens/s
Observed range · dot = median0100200300400tokens/sObserved range · dot = median0100200300400tokens/s

GPT-5.4 Mini · 156 tokens/s median; observed range 47.6 tokens/s–265 tokens/s.

Observed · independent medians

More output than the answer shows.

Visible answer64Hidden reasoning0020406080Visible answer64Hidden reasoning0020406080

Calculated median cost per request: $0.000557.

Visible outputHidden reasoning

Visible output and hidden reasoning are independent medians and are not added together. Request cost is the median of individually priced requests. Hidden reasoning is billed at the output rate.

Published context window: 400,000 tokens.

GPT-5.4 Nano

Collecting

No route for this model has passed the publication threshold.

Published context window: 400,000 tokens.

Unknown

No comparable published API documentation for this pair.

Sources: this page; published model prices (data (JSON)); task assumptions (data (JSON)). Published prices · Observed responses · Calculated scenarios · Assumptions stated with each chart.