Gemini 2.5 Flash Preview is cheaper than GPT-5 Mini at $0.15/M vs $0.25/M input tokens.
| Spec | Gemini 2.5 Flash Preview | GPT-5 Mini |
|---|---|---|
| Input price | $0.15/M tokens | $0.25/M tokens |
| Output price | $0.6/M tokens | $2/M tokens |
| Context window | 1.0M tokens | — |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | Apr 2025 | Aug 2025 |
| SWE-bench Verified | 60.4% | ~70% |
Not enough votes to call it. On the specs, GPT-5 Mini has the edge: newer.
GPT-5 Mini wins Reasoning and Image Generation. Gemini 2.5 Flash Preview costs 3.3x less per token.
Reviewing agent-written code?See a Brief PR report
Gemini 2.5 Flash Preview is cheaper on both: 1.7× input, 3.3× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 11 Sep 2026.
Gemini 2.5 Flash Preview uses 407.5x more bold