GPT-5 Image Mini vs GPT-5.4 Image 2
GPT-5 Image Mini (OpenAI) and GPT-5.4 Image 2 (OpenAI) are listed at different prices. GPT-5 Image Mini costs less: $2.50 per 1M input tokens and $2.00 per 1M output tokens, against $8.00 and $15.00 for GPT-5.4 Image 2. GPT-5 Image Mini has the larger context window, 400,000 tokens against 272,000 for GPT-5.4 Image 2. Only GPT-5.4 Image 2 supports a reasoning effort setting. Both accept text, images and files and produce text and images.
OpenAI: GPT-5 Image Mini and OpenAI: GPT-5.4 Image 2 both accept text, images, and files, produce text and images, and support structured outputs, response formats, and reasoning. Their listed context lengths are 400,000 and 272,000 tokens, respectively; both list a maximum output of 128,000 tokens.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | GPT-5 Image Mini | GPT-5.4 Image 2 |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Added to catalog | 16 Oct 2025 | 21 Apr 2026 |
| Input, per 1M tokens | $2.50 | $8.00 |
| Output, per 1M tokens | $2.00 | $15.00 |
| Cached input read, per 1M | $0.25 | $2.00 |
| Context windowTokens | 400,000 | 272,000 |
| Max outputTokens | 128,000 | 128,000 |
| Accepts | file, image, text | file, image, text |
| Produces | image, text | image, text |
| Tool calling | No | No |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | 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 Image Mini | GPT-5.4 Image 2 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0019 | $0.0085 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.064 | $0.212 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.079 | $0.270 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.378 | $1.22 |
Which to choose
Choose GPT-5 Image Mini if
- Input tokens cost less: $2.50 against $8.00 per 1M
- Output tokens cost less: $2.00 against $15.00 per 1M
- Cached input costs less: $0.25 against $2.00 per 1M
- You need the larger context window: 400,000 tokens against 272,000
Choose GPT-5.4 Image 2 if
- You want to set how much it reasons before it answers
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.