GPT-5.1-Codex-Mini is cheaper than Claude 2 at $1.5/M vs $11.02/M input tokens.
| Spec | Claude 2 | GPT-5.1-Codex-Mini |
|---|---|---|
| Input price | $11.02/M tokens | $1.5/M tokens |
| Output price | $32.68/M tokens | $6/M tokens |
| Context window | 100K tokens | 400K tokens |
| Released | Jun 2023 | Nov 2025 |
Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: bigger model tier, newer, bigger context window.
GPT-5.1-Codex-Mini costs 5.4x less per token.
GPT-5.1-Codex-Mini is cheaper on both — 7.3× input, 5.4× output
GPT-5.1-Codex-Mini uses 56.4x more hedging
GPT-5.1-Codex-Mini is cheaper than Claude 2 at $1.5/M vs $11.02/M input tokens.
| Spec | Claude 2 | GPT-5.1-Codex-Mini |
|---|---|---|
| Input price | $11.02/M tokens | $1.5/M tokens |
| Output price | $32.68/M tokens | $6/M tokens |
| Context window | 100K tokens | 400K tokens |
| Released | Jun 2023 | Nov 2025 |
Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: bigger model tier, newer, bigger context window.
GPT-5.1-Codex-Mini costs 5.4x less per token.
GPT-5.1-Codex-Mini is cheaper on both — 7.3× input, 5.4× output
GPT-5.1-Codex-Mini uses 56.4x more hedging