Qwen3 235B A22B 2507 is cheaper than GPT-5.1-Codex-Mini at $0.00015/M vs $1.5/M input tokens.
| Spec | GPT-5.1-Codex-Mini | Qwen3 235B A22B 2507 |
|---|---|---|
| Input price | $1.5/M tokens | $0.00015/M tokens |
| Output price | $6/M tokens | $0.00085/M tokens |
| Context window | 400K tokens | — |
| Released | Nov 2025 | Jul 2025 |
Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: newer, bigger context window, major provider backing.
Qwen3 235B A22B 2507 costs 7059x less per token.
Qwen3 235B A22B 2507 is cheaper on both — 10000× input, 7059× output
Qwen3 235B A22B 2507 uses 44.8x more emoji
Qwen3 235B A22B 2507 is cheaper than GPT-5.1-Codex-Mini at $0.00015/M vs $1.5/M input tokens.
| Spec | GPT-5.1-Codex-Mini | Qwen3 235B A22B 2507 |
|---|---|---|
| Input price | $1.5/M tokens | $0.00015/M tokens |
| Output price | $6/M tokens | $0.00085/M tokens |
| Context window | 400K tokens | — |
| Released | Nov 2025 | Jul 2025 |
Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: newer, bigger context window, major provider backing.
Qwen3 235B A22B 2507 costs 7059x less per token.
Qwen3 235B A22B 2507 is cheaper on both — 10000× input, 7059× output
Qwen3 235B A22B 2507 uses 44.8x more emoji