Gemini 2.5 Flash Lite Preview vs GPT-6 Luna: cost comparison
Prices updated 2026-10-27 · computed from live provider data
Short answer: Gemini 2.5 Flash Lite Preview is cheaper on a
3:1 input/output blend — $0.175 per million tokens versus
$0.200, a 12% difference.
Gemini 2.5 Flash Lite Preview offers the larger context window at 1,048,576 tokens, against 922,000 for GPT-6 Luna.
Head to head
| Gemini 2.5 Flash Lite Preview | GPT-6 Luna | |
|---|---|---|
| Input, per 1M tokens | $0.100 | $0.100 |
| Output, per 1M tokens | $0.400 | $0.500 |
| Blended 3:1, per 1M | $0.175 | $0.200 |
| Context window | 1,048,576 | 922,000 |
| Vendor | gemini | github_copilot |
Monthly cost at real volumes
| Workload (input / output) | Gemini 2.5 Flash Lite Preview | GPT-6 Luna |
|---|---|---|
| 1M in / 250K out | $0.200 | $0.225 |
| 10M in / 2.5M out | $2.00 | $2.25 |
| 100M in / 25M out | $20.00 | $22.50 |
Which should you pick?
Pick Gemini 2.5 Flash Lite Preview when you need the longer context window (1,048,576 vs 922,000 tokens). Pick Gemini 2.5 Flash Lite Preview when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.