Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Model comparison - Same provider, successor

GPT-5.4 Mini vs GPT-5 Mini

GPT-5.4 Mini and GPT-5 Mini are both OpenAI models. On list price, GPT-5.4 Mini charges 3x GPT-5 Mini's input price ($0.75 vs $0.25 per 1M tokens), and GPT-5.4 Mini charges 2.3x GPT-5 Mini's output price ($4.50 vs $2 per 1M tokens). GPT-5.4 Mini and GPT-5 Mini both have a 400,000-token context window, and both return up to 128,000 output tokens per response. GPT-5.4 Mini was released on March 17, 2026 and GPT-5 Mini on August 7, 2025. Both are closed-weights models, available only through an API.

Last verified from each provider's pricing page. All sources

OpenAI - Closed

GPT-5.4 Mini
Input / 1M
$0.75
Output / 1M
$4.50
Context
400K

OpenAI - Closed

GPT-5 Mini
Input / 1M
$0.25
Output / 1M
$2
Context
400K

Side-by-side specs

SpecGPT-5.4 MiniGPT-5 Mini
ProviderOpenAIOpenAI
Input / 1M tokens$0.75$0.25
Output / 1M tokens$4.50$2
Cache read / 1M$0.075$0.025
Batch input / 1M$0.375$0.125
Batch output / 1M$2.25$1
Context window400,000400,000
Max output128,000128,000
Release date
WeightsClosedClosed
API model idgpt-5.4-minigpt-5-mini
AI Gateway idopenai/gpt-5.4-miniopenai/gpt-5-mini
Last verified

Prices in USD per 1M tokens at each provider's standard first-party rate. A dash means the provider does not bill that item separately or no primary page states it.

What each costs in practice

The same three workloads every model page uses, worked from each model's standard list rates. Swap in your own token counts with the math on each model's page.

WorkloadGPT-5.4 MiniGPT-5 Mini
One agent session1M input tokens and 100K output tokens, no caching.$1.20$0.45
A chat app10,000 requests a day at 2K input and 500 output tokens each.$37.50$1,125.00 per 30-day month$15.00$450.00 per 30-day month
The same session at a 90% cache hit90% of the input is read from the prompt cache. The one-time cache write premium is not included.$0.5925$0.2475
Show the math

GPT-5.4 Mini

  • One agent sessionInput: 1M x $0.75 = $0.75Output: 0.1M x $4.50 = $0.45
  • A chat appInput: 20M x $0.75 = $15.00Output: 5M x $4.50 = $22.50
  • The same session at a 90% cache hitCached input: 0.9M x $0.075 = $0.0675Uncached input: 0.1M x $0.75 = $0.075Output: 0.1M x $4.50 = $0.45

GPT-5 Mini

  • One agent sessionInput: 1M x $0.25 = $0.25Output: 0.1M x $2 = $0.20
  • A chat appInput: 20M x $0.25 = $5.00Output: 5M x $2 = $10.00
  • The same session at a 90% cache hitCached input: 0.9M x $0.025 = $0.0225Uncached input: 0.1M x $0.25 = $0.025Output: 0.1M x $2 = $0.20

Benchmarks under the same setting

Only boards that list both models under the same run setting appear here, one row per board and setting, with each score exactly as the board shows it. Scores on different boards use different scales and are never combined.

Board and settingGPT-5.4 MiniGPT-5 Mini
ProgramBenchmini-SWE-agent, 200 tasksOfficial leaderboard - programbench.com0% resolved (Almost: 0.0%)0% resolved (Almost: 0.0%)

Model pages

FAQ

How do GPT-5.4 Mini and GPT-5 Mini compare on price?

On list price, GPT-5.4 Mini charges 3x GPT-5 Mini's input price ($0.75 vs $0.25 per 1M tokens), and GPT-5.4 Mini charges 2.3x GPT-5 Mini's output price ($4.50 vs $2 per 1M tokens). For one agent session of 1M input and 100K output tokens with no caching, that is $1.20 on GPT-5.4 Mini and $0.45 on GPT-5 Mini. Prices are each provider's first-party list rates, verified October 17, 2026 and October 17, 2026.

What are the context windows of GPT-5.4 Mini and GPT-5 Mini?

GPT-5.4 Mini and GPT-5 Mini both have a 400,000-token context window, and both return up to 128,000 output tokens per response.

Are GPT-5.4 Mini and GPT-5 Mini open weights?

GPT-5.4 Mini is closed-weights and is called through OpenAI's API as gpt-5.4-mini. GPT-5 Mini is closed-weights and is called through OpenAI's API as gpt-5-mini.

More comparisons

Sources

GPT-5.4 Mini verified from developers.openai.com; GPT-5 Mini verified from developers.openai.com. This page is as current as the older of the two: .

Newsletter

Get model price changes as they ship

One email per week. New model releases, price cuts and what they mean for your bill.