Qwen 3 30 B A3 B Fp 8 vs Qwen 3.5 35 B A3 B: cost comparison
Prices updated 2026-11-05 · computed from live provider data
Short answer: Qwen 3 30 B A3 B Fp 8 is cheaper on a
3:1 input/output blend — $0.122 per million tokens versus
$0.158, a 23% difference.
Qwen 3.5 35 B A3 B offers the larger context window at 258,048 tokens, against 32,768 for Qwen 3 30 B A3 B Fp 8.
Head to head
| Qwen 3 30 B A3 B Fp 8 | Qwen 3.5 35 B A3 B | |
|---|---|---|
| Input, per 1M tokens | $0.051 | $0.057 |
| Output, per 1M tokens | $0.335 | $0.459 |
| Blended 3:1, per 1M | $0.122 | $0.158 |
| Context window | 32,768 | 258,048 |
| Vendor | cloudflare | empiriolabs |
Monthly cost at real volumes
| Workload (input / output) | Qwen 3 30 B A3 B Fp 8 | Qwen 3.5 35 B A3 B |
|---|---|---|
| 1M in / 250K out | $0.135 | $0.172 |
| 10M in / 2.5M out | $1.35 | $1.72 |
| 100M in / 25M out | $13.46 | $17.18 |
Which should you pick?
Pick Qwen 3.5 35 B A3 B when you need the longer context window (258,048 vs 32,768 tokens). Pick Qwen 3 30 B A3 B Fp 8 when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.