Gemini 2.5 Flash Preview is cheaper than GPT-5 at $0.15/M vs $1.25/M input tokens.
| Spec | Gemini 2.5 Flash Preview | GPT-5 |
|---|---|---|
| Input price | $0.15/M tokens | $1.25/M tokens |
| Output price | $0.6/M tokens | $10/M tokens |
| Context window | 1.0M tokens | 400K tokens |
| Parameters | Not disclosed | Not disclosed |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | Apr 2025 | Aug 2025 |
| SWE-bench Verified | 60.4% | 74.9% |
Not enough votes to call it. On the specs, GPT-5 has the edge: bigger model tier, newer.
Gemini 2.5 Flash Preview costs 17x less per token.
Gemini 2.5 Flash Preview is cheaper on both: 8.3× input, 17× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Gemini 2.5 Flash Preview uses 21.6x more bold