GPT OSS 20B is cheaper than Mistral Small Creative at $0.02/M vs $0.1/M input tokens.
| Spec | GPT OSS 20B | Mistral Small Creative |
|---|---|---|
| Input price | $0.02/M tokens | $0.1/M tokens |
| Output price | $0.1/M tokens | $0.3/M tokens |
| Context window | 131K tokens | 33K tokens |
| Weights | Open | — |
| Free API (OpenRouter) | No | No |
| Released | Aug 2025 | Dec 2025 |
Not enough votes to call it. On the specs, GPT OSS 20B has the edge: bigger model tier, bigger context window, major provider backing.
GPT OSS 20B is cheaper on both: 5.0× input, 3.0× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Mistral Small Creative uses 10.4x more emoji