Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen2.5 Max | Pixtral Large |
|---|---|---|
| Input ($/M tokens) | $1.6 | $2 |
| Output ($/M tokens) | $6.4 | $6 |
Data from Artificial Analysis API — 12 benchmarks
Qwen2.5 Max is cheaper overall. Its blended price (3:1 input/output ratio) is $2.80/M tokens vs $3.00/M for Pixtral Large.
Qwen2.5 Max wins 7 out of 12 benchmarks compared to 3 for Pixtral Large. See the detailed benchmark chart above for per-category results.
Pixtral Large generates tokens faster at 56 tok/s vs 49 tok/s. However, Pixtral Large has lower time-to-first-token (0.49s vs 1.17s).
Choose based on your priorities: Qwen2.5 Max for lower cost, Qwen2.5 Max for stronger benchmark performance, and Pixtral Large for faster generation. For latency-sensitive apps, check the TTFT comparison above.