GPT OSS 20B is cheaper than Gemini 3 Flash Preview at $0.02/M vs $0.5/M input tokens.
| Spec | Gemini 3 Flash Preview | GPT OSS 20B |
|---|---|---|
| Input price | $0.5/M tokens | $0.02/M tokens |
| Output price | $3/M tokens | $0.1/M tokens |
| Context window | 1.0M tokens | 131K tokens |
| Released | Dec 2025 | Aug 2025 |
Not enough votes to call it. On the specs, Gemini 3 Flash Preview has the edge: newer, bigger context window.
Gemini 3 Flash Preview wins 3 categories, Web Design by the widest margin. GPT OSS 20B costs 30x less per token.
GPT OSS 20B is cheaper on both — 25× input, 30× output
GPT OSS 20B uses 10.2x more emoji
GPT OSS 20B is cheaper than Gemini 3 Flash Preview at $0.02/M vs $0.5/M input tokens.
| Spec | Gemini 3 Flash Preview | GPT OSS 20B |
|---|---|---|
| Input price | $0.5/M tokens | $0.02/M tokens |
| Output price | $3/M tokens | $0.1/M tokens |
| Context window | 1.0M tokens | 131K tokens |
| Released | Dec 2025 | Aug 2025 |
Not enough votes to call it. On the specs, Gemini 3 Flash Preview has the edge: newer, bigger context window.
Gemini 3 Flash Preview wins 3 categories, Web Design by the widest margin. GPT OSS 20B costs 30x less per token.
GPT OSS 20B is cheaper on both — 25× input, 30× output
GPT OSS 20B uses 10.2x more emoji