GPT OSS 20B is cheaper than Qwen3 Next 80B A3B Thinking at $0.02/M vs $0.15/M input tokens.
| Spec | GPT OSS 20B | Qwen3 Next 80B A3B Thinking |
|---|---|---|
| Input price | $0.02/M tokens | $0.15/M tokens |
| Output price | $0.1/M tokens | $1.5/M tokens |
| Context window | 131K tokens | 66K tokens |
| Weights | Open | Open |
| Free API (OpenRouter) | No | No |
| Released | Aug 2025 | Sep 2025 |
Not enough votes to call it. On the specs, nothing separates them.
GPT OSS 20B costs 15x less per token.
GPT OSS 20B is cheaper on both: 7.5× input, 15× output.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Qwen3 Next 80B A3B Thinking uses 9.0x more emoji