GPT-5 nano vs GPT-6 Luna
GPT-5 nano is cheaper than GPT-6 Luna by about 31% on a blended (75% input / 25% output) basis. GPT-5 nano charges $0.0500 / $0.40 per 1M input/output tokens; GPT-6 Luna charges $0.10 / $0.50.
| Field | GPT-5 nano | GPT-6 Luna |
|---|---|---|
| Input $/Mtok | $0.0500 | $0.10 |
| Output $/Mtok | $0.40 | $0.50 |
| Cache read $/Mtok | $0.0050 | $0.0100 |
| Cache write $/Mtok | – | $0.13 |
| Input $/Mchar | 0.0141 | 0.0282 |
| Output $/Mchar | 0.11 | 0.14 |
| Context window | 400000 | 1050000 |
| Tokenizer | o200k | o200k |
| Confidence? | api | official |
| Source | openrouter | official-openai |
Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence
Price history
No price changes recorded yet for either model.
Same workload, monthly cost
Illustrative monthly cost at 10M tokens/month, split per workload preset. Not a substitute for the calculator, which uses your own volume, cache and batch assumptions.
| Workload | GPT-5 nano | GPT-6 Luna |
|---|---|---|
| Coding agent | $0.68 | $1.20 |
| RAG chat | $1.03 | $1.60 |
| Summarisation (batch) | $0.85 | $0.70 |
| Classification | $0.57 | $0.65 |
| Chat assistant | $1.90 | $2.60 |
| Content generation | $3.30 | $3.15 |
Batch pricing not published for GPT-5 nano; standard rate used for the batch share of a workload.
Cite this page
GPT-5 nano vs GPT-6 Luna: $0.0500/$0.40 vs $0.10/$0.50 per 1M tokens as of 2026-11-19. Token Barometer by Dejan Strbad, https://tokenbarometer.com, data CC BY 4.0. https://tokenbarometer.com/compare/openai_gpt-5-nano-vs-openai_gpt-6-luna
GPT-5 nano page | GPT-6 Luna page | Open GPT-5 nano in calculator | Open GPT-6 Luna in calculator