OpenAI
GPT-6 Luna (max)
GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.
OpenAI model releasesModel Snapshot
TypeLanguage
ReleaseSep 22, 2026
Context1,050,000
Tagsexplicit-caching, fast, file-input, implicit-caching
Overall
Rank #71 across 687
37.3
Coding
No rank
n/a
Blended Price
Rank #65 across 432
$0.200/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed167.1 tok/s
First Token44.68s
Max Output128,000
Pricing
Blended$0.200/M
Input$0.100/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 37.3 | #71 |
| LiveBench Mathematics | math | 89.1% | #27 |
| Humanity's Last Exam | reasoning | 38.5% | #81 |
| SciCode | coding, reasoning | 54.6% | #49 |
| Output Speed |