GPT-6 Luna vs GPT-5 nano: price comparison
Real 2026 API prices side by side, with the total cost of a typical 10M-input / 3M-output monthly workload.
Price & cost at a glance
| GPT-6 Luna | GPT-5 nano | |
|---|---|---|
| Input / 1M tokens | $0.1 | $0.1 |
| Output / 1M tokens | $0.5 | $0.4 |
| Context window | 272K | 400K |
| Cost — 10M in + 3M out | $2.5 | $2.2 |
Green = cheaper / larger. Prices per 1M tokens, USD. Snapshot 2026 — verify with the provider.
Which is cheaper?
Run your own token mix in the cost calculator, or see each model in depth: GPT-6 Luna · GPT-5 nano.
Frequently asked
Is GPT-6 Luna or GPT-5 nano cheaper?
At a typical 10M input + 3M output tokens per month, GPT-5 nano costs about $2.2 versus $2.5 for GPT-6 Luna — GPT-5 nano is roughly 1.1x cheaper on this workload. Your ratio of input to output tokens changes the gap.
What's the price difference between GPT-6 Luna and GPT-5 nano?
GPT-6 Luna is $0.1/$0.5 per 1M input/output tokens; GPT-5 nano is $0.1/$0.4. Output tokens usually dominate a bill, so compare the output price first.
Which has the bigger context window, GPT-6 Luna or GPT-5 nano?
GPT-6 Luna supports about 272K tokens and GPT-5 nano about 400K. A bigger window costs more per call because every token in context is billed.
Related comparisons
Educational estimates — not affiliated with any provider.