Gemini 1.5 Flash-8B vs Gemini 2.5 Flash-Lite
Sample workload: short support reply (~512 output tokens). Open the calculator for your own prompt.
Estimate Gemini 1.5 Flash-8B · Estimate Gemini 2.5 Flash-Lite
| Field | Gemini 1.5 Flash-8B | Gemini 2.5 Flash-Lite |
|---|---|---|
| Provider | ||
| Accuracy | Approx | Approx |
| Input / 1M | $0.037/1M | $0.100/1M |
| Output / 1M | $0.150/1M | $0.400/1M |
| Sample input tokens | 25 | 25 |
| Sample request cost | $0.000078 | $0.000207 |
| 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.
Gemini 1.5 Flash-8B in calculator · Gemini 2.5 Flash-Lite in calculator · Count tokens (Gemini 1.5 Flash-8B) · Count tokens (Gemini 2.5 Flash-Lite) · All comparisons
How LLM pricing works · Exact vs Approx · Gemini 1.5 Flash-8B page · Gemini 2.5 Flash-Lite page