GPT-5.6 Luna
RestrictedClosed
The fastest, most cost-efficient tier of OpenAI's GPT-5.6 family, available in limited preview through the OpenAI API and Codex for approved organizations.
Cite
Notes
Only stored in your browser.
Context
1.1M
Input
$0.20
/1M tok
Output
$1.20
/1M tok
Blended
$0.45
#283/ 454/1M · 3:1
Speed
132
#38/ 454tok/s
Cache read
$0.02
0.10x input
Cache write
$0.25
1.25x input
Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter
| Reasoning effort | Index | Speed |
|---|---|---|
| max | 52.3 | 132 t/s |
| xhigh | 50.1 | 133 t/s |
| high | 47.0 | 137 t/s |
| medium | 38.9 | 125 t/s |
| low | 33.9 | 123 t/s |
| Non-reasoning | 26.8 | 125 t/s |
Intelligence Index per reasoning-effort setting, via Artificial Analysis · pricing identical across tiers
Reported on 17 evals across 10 domains - best 84.4% on MedScribe · #19 of 70
Reported eval scores
17TaxEval v276.2
MortgageTax67.3
CorpFin v264.2
Vals Index59.9
SciCode39.9
GPQA Diamond64.5
MedScribe84.4
MedCode42.4
SAGE44.2
EQ-Bench 41156.3