PaLM 2 Chat is cheaper than GPT-3.5 Turbo at $0.5/M vs $1.5/M input tokens.
| Spec | GPT-3.5 Turbo | PaLM 2 Chat |
|---|---|---|
| Input price | $1.5/M tokens | $0.5/M tokens |
| Output price | $2/M tokens | $0.5/M tokens |
| Context window | 16K tokens | 8K tokens |
| Released | Mar 2022 | Jul 2023 |
Not enough votes to call it. On the specs, PaLM 2 Chat has the edge: bigger model tier, newer.
PaLM 2 Chat costs 4.0x less per token.
PaLM 2 Chat is cheaper on both — 3.0× input, 4.0× output
PaLM 2 Chat uses 335.2x more bold
PaLM 2 Chat is cheaper than GPT-3.5 Turbo at $0.5/M vs $1.5/M input tokens.
| Spec | GPT-3.5 Turbo | PaLM 2 Chat |
|---|---|---|
| Input price | $1.5/M tokens | $0.5/M tokens |
| Output price | $2/M tokens | $0.5/M tokens |
| Context window | 16K tokens | 8K tokens |
| Released | Mar 2022 | Jul 2023 |
Not enough votes to call it. On the specs, PaLM 2 Chat has the edge: bigger model tier, newer.
PaLM 2 Chat costs 4.0x less per token.
PaLM 2 Chat is cheaper on both — 3.0× input, 4.0× output
PaLM 2 Chat uses 335.2x more bold