GPT OSS 120B is cheaper than Qwen3.6 27B at $0.18/M vs $0.325/M input tokens.
| Spec | GPT OSS 120B | Qwen3.6 27B |
|---|---|---|
| Input price | $0.18/M tokens | $0.325/M tokens |
| Output price | $0.8/M tokens | $3.25/M tokens |
| Context window | 131K tokens | 256K tokens |
| Released | Aug 2025 | Apr 2026 |
Not enough votes to call it. On the specs, nothing separates them.
GPT OSS 120B costs 4.1x less per token.
GPT OSS 120B is cheaper on both — 1.8× input, 4.1× output
Qwen3.6 27B uses 10.0x more emoji
GPT OSS 120B is cheaper than Qwen3.6 27B at $0.18/M vs $0.325/M input tokens.
| Spec | GPT OSS 120B | Qwen3.6 27B |
|---|---|---|
| Input price | $0.18/M tokens | $0.325/M tokens |
| Output price | $0.8/M tokens | $3.25/M tokens |
| Context window | 131K tokens | 256K tokens |
| Released | Aug 2025 | Apr 2026 |
Not enough votes to call it. On the specs, nothing separates them.
GPT OSS 120B costs 4.1x less per token.
GPT OSS 120B is cheaper on both — 1.8× input, 4.1× output
Qwen3.6 27B uses 10.0x more emoji