Loading model details
OpenAI
Hosted by a provider reached through SayGM. The route is sealed in transit and in use; the provider receives the prompt under its API terms.
Released
Jul 2026Knowledge cutoff
Feb 2026Modalities
Text · Tool calling · Image inputBest price on SayGM
-25.0%In
Cached
Out
per Mtok*
SayGM's best available rate for gpt-5.6-luna next to OpenAI's own published list price — 25.0% off.
| Dimension | SayGM price | OpenAI list price |
|---|---|---|
| Input | $0.15per Mtok | $0.20 |
| Output | $0.90per Mtok | $1.20 |
| Cache read | $0.015per Mtok | $0.02 |
| Cache write | $0.1875per Mtok | $0.25 |
| Long-context inputabove 272,000 input tokens | $0.30per Mtok | $0.40 |
| Long-context outputabove 272,000 input tokens | $1.35per Mtok | $1.80 |
| Long-context cache readabove 272,000 input tokens | $0.03per Mtok | $0.04 |
| Long-context cache writeabove 272,000 input tokens | $0.375per Mtok | $0.50 |
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.17
$0.20Cached input
$0.02
Output
$1.02
$1.20Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.
Measured over 8 windows: 3,050 requests and 2,023,781 input-side tokens. Most recent window closed 2026-09-16 15:09 UTC.
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 25.0% off | $0.15 | $0.90 |
| Provider 2 | 20.0% off | $0.16 | $0.96 |
| Provider 3 | 16.1% off | $0.17 | $1.01 |
| Provider 4 | 16.1% off | $0.17 | $1.01 |
| Provider 5 | 16.0% off | $0.17 | $1.01 |
| Provider 6 | 15.0% off | $0.17 | $1.02 |
| Provider 7 | 14.0% off | $0.17 | $1.03 |
| Provider 8 | 13.5% off | $0.17 | $1.04 |
| Provider 9 | 13.0% off | $0.17 | $1.04 |
Measured on the requests SayGM routed to this model.
Fixed-seed suites SayGM runs against this model.
The best available rate for gpt-5.6-luna on SayGM right now is $0.15 per million input tokens and $0.90 per million output tokens. A request above 272,000 input tokens bills at SayGM's long-context rate instead.
SayGM's best available rate for gpt-5.6-luna is 25.0% off OpenAI's list price.
Yes. gpt-5.6-luna is served on SayGM's OpenAI-compatible chat/completions surface, so an unmodified OpenAI SDK pointed at SayGM's base URL works with it.