GPT-4o (Omni) is cheaper than Llama 3.1 405B at $2.5/M vs $2.7/M input tokens.
| Spec | GPT-4o (Omni) | Llama 3.1 405B |
|---|---|---|
| Input price | $2.5/M tokens | $2.7/M tokens |
| Output price | $10/M tokens | $3.1/M tokens |
| Context window | 128K tokens | 128K tokens |
| Parameters | Not disclosed | 405B |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | No |
| Released | May 2024 | Jul 2024 |
| MMLU | 88.7% | 88.6% |
Not enough votes to call it. On the specs, nothing separates them.
Llama 3.1 405B costs 3.2x less per token.
Reviewing agent-written code?See a Brief PR report
GPT-4o (Omni) wins input (1.1× cheaper)·Llama 3.1 405B wins output (3.2× cheaper)
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 23 Sep 2026.
GPT-4o (Omni) uses 734.5x more bold