GPT-3.5 Turbo is cheaper than Llama 3.1 405B at $1.5/M vs $2.7/M input tokens.
| Spec | GPT-3.5 Turbo | Llama 3.1 405B |
|---|---|---|
| Input price | $1.5/M tokens | $2.7/M tokens |
| Output price | $2/M tokens | $3.1/M tokens |
| Context window | 16K tokens | 128K tokens |
| Parameters | Not disclosed | 405B |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | No |
| Released | Mar 2022 | Jul 2024 |
Not enough votes to call it. On the specs, Llama 3.1 405B has the edge: bigger model tier, newer, bigger context window.
Reviewing agent-written code?See a Brief PR report
GPT-3.5 Turbo is cheaper on both: 1.8× input, 1.6× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 11 Sep 2026.
GPT-3.5 Turbo uses 30.8x more bold