GPT-4o mini vs Gemini 2.5 Flash
Sample workload: short support reply (~512 output tokens). Open the calculator for your own prompt.
| Field | GPT-4o mini | Gemini 2.5 Flash |
|---|---|---|
| Provider | OpenAI | |
| Accuracy | Exact | Approx |
| Input / 1M | $0.150/1M | $0.300/1M |
| Output / 1M | $0.600/1M | $2.50/1M |
| Sample input tokens | 16 | 25 |
| Sample request cost | $0.00031 | $0.001287 |
| 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.
GPT-4o mini in calculator · Gemini 2.5 Flash in calculator · Count tokens (GPT-4o mini) · Count tokens (Gemini 2.5 Flash) · All comparisons
How LLM pricing works · Exact vs Approx · GPT-4o mini page · Gemini 2.5 Flash page