GPT-4o (Omni) is cheaper than Gemini 1.5 Pro at $2.5/M vs $3.5/M input tokens.
| Spec | Gemini 1.5 Pro | GPT-4o (Omni) |
|---|---|---|
| Input price | $3.5/M tokens | $2.5/M tokens |
| Output price | $10.5/M tokens | $10/M tokens |
| Context window | 1.0M tokens | 128K tokens |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | Feb 2024 | May 2024 |
| MMLU | 86.0% | 88.7% |
Not enough votes to call it. On the specs, GPT-4o (Omni) has the edge: bigger model tier, newer.
Reviewing agent-written code?See a Brief PR report
GPT-4o (Omni) is cheaper on both: 1.4× input, 1.1× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 13 Sep 2026.
GPT-4o (Omni) uses 2.5x more emoji