GPT-4o mini is cheaper than Kimi Linear 48B A3B Instruct at $0.15/M vs $0.3/M input tokens.
| Spec | GPT-4o mini | Kimi Linear 48B A3B Instruct |
|---|---|---|
| Input price | $0.15/M tokens | $0.3/M tokens |
| Output price | $0.6/M tokens | $0.6/M tokens |
| Context window | 128K tokens | 1.0M tokens |
| Released | Jul 2024 | 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-4o mini uses 5.0x more transitions
GPT-4o mini is cheaper than Kimi Linear 48B A3B Instruct at $0.15/M vs $0.3/M input tokens.
| Spec | GPT-4o mini | Kimi Linear 48B A3B Instruct |
|---|---|---|
| Input price | $0.15/M tokens | $0.3/M tokens |
| Output price | $0.6/M tokens | $0.6/M tokens |
| Context window | 128K tokens | 1.0M tokens |
| Released | Jul 2024 | 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-4o mini uses 5.0x more transitions