GPT OSS 120B is cheaper than Claude 3.7 Thinking Sonnet at $0.18/M vs $6/M input tokens.
| Spec | Claude 3.7 Thinking Sonnet | GPT OSS 120B |
|---|---|---|
| Input price | $6/M tokens | $0.18/M tokens |
| Output price | $30/M tokens | $0.8/M tokens |
| Context window | 200K tokens | 131K tokens |
| Released | Feb 2025 | Aug 2025 |
| MMLU | 77.1% | Matches/exceeds o4-mini |
Not enough votes to call it. On the specs, GPT OSS 120B has the edge: bigger model tier, newer.
GPT OSS 120B costs 38x less per token.
GPT OSS 120B is cheaper on both — 33× input, 38× output
GPT OSS 120B uses 15.4x more emoji
GPT OSS 120B is cheaper than Claude 3.7 Thinking Sonnet at $0.18/M vs $6/M input tokens.
| Spec | Claude 3.7 Thinking Sonnet | GPT OSS 120B |
|---|---|---|
| Input price | $6/M tokens | $0.18/M tokens |
| Output price | $30/M tokens | $0.8/M tokens |
| Context window | 200K tokens | 131K tokens |
| Released | Feb 2025 | Aug 2025 |
| MMLU | 77.1% | Matches/exceeds o4-mini |
Not enough votes to call it. On the specs, GPT OSS 120B has the edge: bigger model tier, newer.
GPT OSS 120B costs 38x less per token.
GPT OSS 120B is cheaper on both — 33× input, 38× output
GPT OSS 120B uses 15.4x more emoji