Index · comparison
Gemini 3.6 Flash vs GPT-4o mini
GPT-4o mini is 83% cheaper than Gemini 3.6 Flash ($0.75 vs $4.50 blended per 1M tokens).
Gemini 3.6 Flash on Google vs GPT-4o mini on OpenAI — price performance. Every figure below is the value shown on each model's own endpoint page, with its source and verification date.
| Metric | Gemini 3.6 Flash | GPT-4o mini |
|---|---|---|
| Input $/1M | $0.75 | $0.15 |
| Output $/1M | $3.75 | $0.6 |
| Blended $/1M | $4.5 | $0.75 |
| Context window | 1M | 128K |
| Max output | 64K | 16K |
| Intelligence index | 51.6 | 6.7 |
Highlighted cell = better on that row (lower price/latency, higher context/intelligence/throughput). "—" = not measured for that model.
Which to pick
On blended token price, GPT-4o mini is the cheaper of the two ($0.75 vs $4.5 per 1M). Price alone rarely settles it: check the intelligence index and latency rows above against your workload, and open each endpoint page for the full price history and provider terms.
Sources: Gemini 3.6 Flash endpoint · GPT-4o mini endpoint · Gemini 3.6 Flash price verified 2026-09-03 · GPT-4o mini price verified 2026-09-05