MiniMax M1 has a larger context window than GPT-2 (1.0M tokens vs 1K tokens).
| Spec | GPT-2 | MiniMax M1 |
|---|---|---|
| Input price | — | $0.3/M tokens |
| Output price | — | $1.65/M tokens |
| Context window | 1K tokens | 1.0M tokens |
| Parameters | 1.5B | 456B (45.9B active) |
| Weights | Open | Open |
| Free API (OpenRouter) | — | No |
| Released | Nov 2019 | Jun 2025 |
Not enough votes to call it. On the specs, MiniMax M1 has the edge: bigger model tier, newer, bigger context window.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
MiniMax M1 uses 53.8x more hedging