GPT-3.5 Turbo is cheaper than o1 at $1.5/M vs $15/M input tokens.
| Spec | GPT-3.5 Turbo | o1 |
|---|---|---|
| Input price | $1.5/M tokens | $15/M tokens |
| Output price | $2/M tokens | $60/M tokens |
| Context window | 16K tokens | 128K tokens |
| Released | Mar 2022 | Dec 2024 |
Not enough votes to call it. On the specs, o1 has the edge: newer, bigger context window.
GPT-3.5 Turbo costs 30x less per token.
GPT-3.5 Turbo is cheaper on both — 10× input, 30× output
o1 uses 503.7x more bold
GPT-3.5 Turbo is cheaper than o1 at $1.5/M vs $15/M input tokens.
| Spec | GPT-3.5 Turbo | o1 |
|---|---|---|
| Input price | $1.5/M tokens | $15/M tokens |
| Output price | $2/M tokens | $60/M tokens |
| Context window | 16K tokens | 128K tokens |
| Released | Mar 2022 | Dec 2024 |
Not enough votes to call it. On the specs, o1 has the edge: newer, bigger context window.
GPT-3.5 Turbo costs 30x less per token.
GPT-3.5 Turbo is cheaper on both — 10× input, 30× output
o1 uses 503.7x more bold