OpenAI Codex Mini is cheaper than Qwen3.8 Max Prime at $1.5/M vs $4/M input tokens.
| Spec | OpenAI Codex Mini | Qwen3.8 Max Prime |
|---|---|---|
| Input price | $1.5/M tokens | $4/M tokens |
| Output price | $6/M tokens | $12/M tokens |
| Context window | 200K tokens | 1.0M tokens |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | May 2025 | Sep 2026 |
Not enough votes to call it. On the specs, Qwen3.8 Max Prime has the edge: bigger model tier, newer, bigger context window.
Reviewing agent-written code?See a Brief PR report
OpenAI Codex Mini is cheaper on both: 2.7× input, 2.0× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 25 Sep 2026.