GPT OSS 120B is cheaper than Qwen3.5 397B A17B at $0.18/M vs $0.6/M input tokens.
| Spec | GPT OSS 120B | Qwen3.5 397B A17B |
|---|---|---|
| Input price | $0.18/M tokens | $0.6/M tokens |
| Output price | $0.8/M tokens | $3.6/M tokens |
| Context window | 131K tokens | 262K tokens |
| Released | Aug 2025 | Feb 2026 |
Not enough votes to call it. On the specs, nothing separates them.
GPT OSS 120B costs 4.5x less per token.
GPT OSS 120B is cheaper on both — 3.3× input, 4.5× output
Qwen3.5 397B A17B uses 2.3x more lists
GPT OSS 120B is cheaper than Qwen3.5 397B A17B at $0.18/M vs $0.6/M input tokens.
| Spec | GPT OSS 120B | Qwen3.5 397B A17B |
|---|---|---|
| Input price | $0.18/M tokens | $0.6/M tokens |
| Output price | $0.8/M tokens | $3.6/M tokens |
| Context window | 131K tokens | 262K tokens |
| Released | Aug 2025 | Feb 2026 |
Not enough votes to call it. On the specs, nothing separates them.
GPT OSS 120B costs 4.5x less per token.
GPT OSS 120B is cheaper on both — 3.3× input, 4.5× output
Qwen3.5 397B A17B uses 2.3x more lists