GPT OSS 20B is cheaper than Gemini 3.7 Flash at $0.02/M vs $0.375/M input tokens.
| Spec | Gemini 3.7 Flash | GPT OSS 20B |
|---|---|---|
| Input price | $0.375/M tokens | $0.02/M tokens |
| Output price | $1.875/M tokens | $0.1/M tokens |
| Context window | 1.0M tokens | 131K tokens |
| Released | Aug 2026 | Aug 2025 |
Not enough votes to call it. On the specs, Gemini 3.7 Flash has the edge: newer, bigger context window.
GPT OSS 20B costs 19x less per token.
GPT OSS 20B is cheaper on both — 19× input, 19× output
GPT OSS 20B uses 10.2x more emoji
GPT OSS 20B is cheaper than Gemini 3.7 Flash at $0.02/M vs $0.375/M input tokens.
| Spec | Gemini 3.7 Flash | GPT OSS 20B |
|---|---|---|
| Input price | $0.375/M tokens | $0.02/M tokens |
| Output price | $1.875/M tokens | $0.1/M tokens |
| Context window | 1.0M tokens | 131K tokens |
| Released | Aug 2026 | Aug 2025 |
Not enough votes to call it. On the specs, Gemini 3.7 Flash has the edge: newer, bigger context window.
GPT OSS 20B costs 19x less per token.
GPT OSS 20B is cheaper on both — 19× input, 19× output
GPT OSS 20B uses 10.2x more emoji