Gemini 2.5 Flash Preview is cheaper than OpenAI o4 Mini High at $0.15/M vs $1.1/M input tokens.
| Spec | Gemini 2.5 Flash Preview | OpenAI o4 Mini High |
|---|---|---|
| Input price | $0.15/M tokens | $1.1/M tokens |
| Output price | $0.6/M tokens | $4.4/M tokens |
| Context window | 1.0M tokens | 200K tokens |
| Parameters | Not disclosed | Not disclosed |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | Apr 2025 | Apr 2025 |
| SWE-bench Verified | 60.4% | 68.1% |
Not enough votes to call it. On the specs, nothing separates them.
OpenAI o4 Mini High takes Image Generation. Gemini 2.5 Flash Preview costs 7.3x less per token.
Gemini 2.5 Flash Preview is cheaper on both: 7.3× input, 7.3× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Gemini 2.5 Flash Preview uses 407.5x more bold