gpt-5.6-luna pricing
Per million tokens, in US dollars. Synced from the public price feeds on 2026-08-07, and these are the same numbers KostLens bills from.
What it costs
| Provider | Input | Output | Cached input | Cache write | Cache write, 1h |
|---|---|---|---|---|---|
| azure | $0.200 | $1.20 | $0.020 | - | - |
| openai | $1.00 | $6.00 | $0.100 | - | - |
A dash means the provider does not publish that rate, not that it is free.
The same model is not the same price
gpt-5.6-luna is sold by 2 providers here, and the dearest charges 400% more per input token than the cheapest: $1.00 on openai against $0.200 on azure. That gap is real money on a workload of any size, and it is invisible in a provider console, which only ever shows you its own bill.
Long prompts reprice the whole call
Past 272k tokens of input, azure bills gpt-5.6-luna at a different rate: $0.400 input and $1.80 output . Not the tokens past the threshold: the whole call. A long-context workload that crosses it on some requests and not others has two prices, and averaging them is how a forecast goes wrong.
Know what this costs you, per customer
These are list prices. What they turn into on your bill depends on your token mix, and which of your customers is generating it. KostLens wraps your existing client in three lines, reads the usage the provider already returns, and gives you cost per customer and per feature. Your prompts and API keys never touch our servers.