GPT-5.1 Codex Max vs Qwen3 Coder Plus
30-second takeaway
- Qwen3 Coder Plus has the cheaper input: $1 vs $1.25 (per 1M tokens, 20% less)
- Qwen3 Coder Plus has the larger context: 1.049M vs 400K tokens
| GPT-5.1 Codex Max Abacus | Qwen3 Coder Plus Alibaba | |
|---|---|---|
| Input | $1.25 | $1 |
| Output | $10 | $5 |
| Context | 400K | 1.049M |
More specs (max output / capabilities)
| max output | 128,000 | 65,536 |
| Reasoning | ✓ Yes | — No |
| Tool calls | ✓ Yes | ✓ Yes |
| Open weights | — No | ✓ Yes |
Prices are official/data-source rates (per 1M tokens), not what relays actually charge — relay prices vary with discounts and group multipliers. See methodology.