GPT OSS 20B is cheaper than Kimi Linear 48B A3B Instruct at $0.02/M vs $0.3/M input tokens.
| Spec | GPT OSS 20B | Kimi Linear 48B A3B Instruct |
|---|---|---|
| Input price | $0.02/M tokens | $0.3/M tokens |
| Output price | $0.1/M tokens | $0.6/M tokens |
| Context window | 131K tokens | 1.0M tokens |
| Released | Aug 2025 | Nov 2025 |
Not enough votes to call it. On the specs, Kimi Linear 48B A3B Instruct has the edge: bigger model tier, newer, bigger context window.
GPT OSS 20B costs 6.0x less per token.
GPT OSS 20B is cheaper on both — 15× input, 6.0× output
GPT OSS 20B uses 10.2x more emoji
GPT OSS 20B is cheaper than Kimi Linear 48B A3B Instruct at $0.02/M vs $0.3/M input tokens.
| Spec | GPT OSS 20B | Kimi Linear 48B A3B Instruct |
|---|---|---|
| Input price | $0.02/M tokens | $0.3/M tokens |
| Output price | $0.1/M tokens | $0.6/M tokens |
| Context window | 131K tokens | 1.0M tokens |
| Released | Aug 2025 | Nov 2025 |
Not enough votes to call it. On the specs, Kimi Linear 48B A3B Instruct has the edge: bigger model tier, newer, bigger context window.
GPT OSS 20B costs 6.0x less per token.
GPT OSS 20B is cheaper on both — 15× input, 6.0× output
GPT OSS 20B uses 10.2x more emoji