Qwen 3.6 35 B A3 B vs GPT Luna Latest: cost comparison
Prices updated 2026-11-09 · computed from live provider data
Short answer: GPT Luna Latest is cheaper on a
3:1 input/output blend — $0.200 per million tokens versus
$0.300, a 33% difference.
GPT Luna Latest offers the larger context window at 1,050,000 tokens, against 262,144 for Qwen 3.6 35 B A3 B.
Head to head
| Qwen 3.6 35 B A3 B | GPT Luna Latest | |
|---|---|---|
| Input, per 1M tokens | $0.100 | $0.100 |
| Output, per 1M tokens | $0.900 | $0.500 |
| Blended 3:1, per 1M | $0.300 | $0.200 |
| Context window | 262,144 | 1,050,000 |
| Vendor | qwen | openai |
Monthly cost at real volumes
| Workload (input / output) | Qwen 3.6 35 B A3 B | GPT Luna Latest |
|---|---|---|
| 1M in / 250K out | $0.325 | $0.225 |
| 10M in / 2.5M out | $3.25 | $2.25 |
| 100M in / 25M out | $32.50 | $22.50 |
Which should you pick?
Pick GPT Luna Latest when you need the longer context window (1,050,000 vs 262,144 tokens). Pick GPT Luna Latest when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.