Ripple 65 B Preview vs GPT Luna Latest: cost comparison
Prices updated 2026-11-14 · computed from live provider data
Short answer: Ripple 65 B Preview is cheaper on a
3:1 input/output blend — $0.150 per million tokens versus
$0.200, a 25% difference.
GPT Luna Latest offers the larger context window at 1,050,000 tokens, against 1,048,576 for Ripple 65 B Preview.
Head to head
| Ripple 65 B Preview | GPT Luna Latest | |
|---|---|---|
| Input, per 1M tokens | $0.100 | $0.100 |
| Output, per 1M tokens | $0.300 | $0.500 |
| Blended 3:1, per 1M | $0.150 | $0.200 |
| Context window | 1,048,576 | 1,050,000 |
| Vendor | ricursiveai | openai |
Monthly cost at real volumes
| Workload (input / output) | Ripple 65 B Preview | GPT Luna Latest |
|---|---|---|
| 1M in / 250K out | $0.175 | $0.225 |
| 10M in / 2.5M out | $1.75 | $2.25 |
| 100M in / 25M out | $17.50 | $22.50 |
Which should you pick?
Pick GPT Luna Latest when you need the longer context window (1,050,000 vs 1,048,576 tokens). Pick Ripple 65 B Preview when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.