GPT-5.4 Mini vs GPT Mini Latest
GPT-5.4 Mini (OpenAI) and GPT Mini Latest (OpenAI) have the same list price: $0.75 per 1M input tokens and $4.50 per 1M output tokens. Both hold 400,000 tokens of context. Both accept text, images and files and produce text.
OpenAI: GPT-5.4 Mini and OpenAI: GPT Mini Latest both accept text, images, and files, produce text, support tools and structured outputs, and have 400,000-token contexts with 128,000-token output limits. GPT Mini Latest redirects to the latest model in the GPT Mini family.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | GPT-5.4 Mini | GPT Mini Latest |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Added to catalog | 17 Mar 2026 | 27 Apr 2026 |
| Input, per 1M tokens | $0.75 | $0.75 |
| Output, per 1M tokens | $4.50 | $4.50 |
| Cached input read, per 1M | $0.075 | $0.075 |
| Context windowTokens | 400,000 | 400,000 |
| Max outputTokens | 128,000 | 128,000 |
| Accepts | file, image, text | file, image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | Yes | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | GPT-5.4 Mini | GPT Mini Latest |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0017 | $0.0017 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.022 | $0.022 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.032 | $0.032 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.119 | $0.119 |
Which to choose
Choose GPT-5.4 Mini if
No row of the table favours GPT-5.4 Mini. The difference, if there is one, is in the answers it writes: try it on your own task.
GPT-5.4 Mini detailsChoose GPT Mini Latest if
No row of the table favours GPT Mini Latest. The difference, if there is one, is in the answers it writes: try it on your own task.
GPT Mini Latest detailsNeither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.