GPT OSS 20B is cheaper than GPT-3.5 Turbo at $0.02/M vs $1.5/M input tokens.
| Spec | GPT-3.5 Turbo | GPT OSS 20B |
|---|---|---|
| Input price | $1.5/M tokens | $0.02/M tokens |
| Output price | $2/M tokens | $0.1/M tokens |
| Context window | 16K tokens | 131K tokens |
| Released | Mar 2022 | Aug 2025 |
Not enough votes to call it. On the specs, GPT OSS 20B has the edge: bigger model tier, newer, bigger context window.
GPT OSS 20B wins Web Design and Image Generation. GPT OSS 20B costs 20x less per token.
GPT OSS 20B is cheaper on both — 75× input, 20× output
GPT OSS 20B uses 10.2x more emoji
GPT OSS 20B is cheaper than GPT-3.5 Turbo at $0.02/M vs $1.5/M input tokens.
| Spec | GPT-3.5 Turbo | GPT OSS 20B |
|---|---|---|
| Input price | $1.5/M tokens | $0.02/M tokens |
| Output price | $2/M tokens | $0.1/M tokens |
| Context window | 16K tokens | 131K tokens |
| Released | Mar 2022 | Aug 2025 |
Not enough votes to call it. On the specs, GPT OSS 20B has the edge: bigger model tier, newer, bigger context window.
GPT OSS 20B wins Web Design and Image Generation. GPT OSS 20B costs 20x less per token.
GPT OSS 20B is cheaper on both — 75× input, 20× output
GPT OSS 20B uses 10.2x more emoji