o4-mini vs GPT-5 Mini
Sample workload: short support reply (~512 output tokens). Open the calculator for your own prompt.
| Field | o4-mini | GPT-5 Mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Accuracy | Exact | Exact |
| Input / 1M | $1.10/1M | $0.250/1M |
| Output / 1M | $4.40/1M | $2.00/1M |
| Sample input tokens | 16 | 16 |
| Sample request cost | $0.00227 | $0.001028 |
| Pages | Model page | Model page |
Try your own prompt
Sample costs above use a fixed support-chat prompt. For your text, open the main calculator with either model preselected.
o4-mini in calculator · GPT-5 Mini in calculator · Count tokens (o4-mini) · Count tokens (GPT-5 Mini) · All comparisons
How LLM pricing works · Exact vs Approx · o4-mini page · GPT-5 Mini page
Related tools
LLM cost calculator · Cheapest LLM API · Cache savings · Batch pricing
Related guides
How LLM API pricing works · How prompt cost is calculated · Prompt caching explained · Exact vs Approx
Sources and references
Official documentation used for definitions, counting methods, or rate cards. Always confirm critical budgets on the provider page.