GPT-5.6 Luna
OpenAI · Released 9 Jul 2026 · gpt-5.6-luna
$0.20
Input price / 1M tokens
#6 of 61, cheapest first
$1.20
Output price / 1M tokens
#8 of 61, cheapest first
1.05M
Context window
#2 of 71
124
Output tokens / second
#23 of 61
62.7%
SWE-bench Pro
#4 of 16
67.2%
DeepSWE v1.1
#11 of 17
84.7%
Terminal-Bench 2.1
#10 of 17
45.6%
OSWorld 2.0
#10 of 10
Summary
GPT-5.6 Luna is a proprietary model from OpenAI, released on 9 Jul 2026.
At $0.20 input and $1.20 output per million tokens, it is #6 of 61 on input price, cheapest first.
Its 1.05M-token context window ranks #2 of 71.
Measured output speed is 124 tokens per second, #23 of 61.
The fastest and most affordable GPT-5.6 tier, for cost-sensitive, high-volume workloads. It is the successor to the earlier 'nano' tier.
Benchmarks · 5 reported
| Benchmark | Score | Bar | Rank | Source |
|---|---|---|---|---|
| SWE-bench Pro | 62.7% | #4 of 16 | OpenAI launch postSelf-reported | |
| DeepSWE v1.1 | 67.2% | #11 of 17 | OpenAI launch postSelf-reported | |
| Terminal-Bench 2.1 | 84.7% | #10 of 17 | OpenAI launch postSelf-reported | |
| OSWorld 2.0 | 45.6% | #10 of 10 | OpenAI launch postSelf-reported | |
| GPQA Diamond | 92.3% | #11 of 27 | OpenAI launch postSelf-reported |
Self-reported means the lab ran the test itself. A rank appears only where several labs report the same version of a benchmark.
Similar models
Models with the most benchmarks in common with GPT-5.6 Luna, and the closest scores.
SWE-bench Pro
#4 of 16Harder multi-file engineering tasks
- GPT-5.6 Luna62.7
- GPT-5.6 Terra63.4
- GPT-5.6 Sol64.6
- GLM-5.262.1
DeepSWE v1.1
#11 of 17Long coding tasks in real repos
- GPT-5.6 Luna67.2
- GPT-5.6 Terra69.6
- GPT-5.6 Sol72.7
- Kimi K367.5
- Gemini 3.7 Flash65.3
Terminal-Bench 2.1
#10 of 17Terminal tasks, earlier set
- GPT-5.6 Luna84.7
- GPT-5.6 Terra87.4
- GPT-5.6 Sol88.8
- Kimi K388.3
- Gemini 3.7 Flash85.8
- GLM-5.281
OSWorld 2.0
#10 of 10Long desktop and web workflows
- GPT-5.6 Luna45.6
- GPT-5.6 Terra50.2
- GPT-5.6 Sol62.6
- Gemini 3.7 Flash47.9
Compare GPT-5.6 Luna side by side
Pre-filled with the two closest models. Swap any of them.
Sources
- price, tiers, long-context rule: developers.openai.com/api/docs/pricing, checked 2 Oct 2026
- context, max output, knowledge cutoff, modalities, api id: developers.openai.com/api/docs/models/gpt-5.6-luna, checked 2 Oct 2026
- release date, Jul 30 price cut: developers.openai.com/api/docs/changelog, checked 2 Oct 2026
- launch price, benchmarks: openai.com/index/gpt-5-6/, checked 2 Oct 2026
- output speed: artificialanalysis.ai/models/gpt-5-6-luna, checked 2 Oct 2026
Building on GPT-5.6 Luna?
Get the architecture right before the bill arrives.
We size caching, routing and fallbacks for your workload on a free call, and tell you where a cheaper model is good enough.