GPT-5.6 Luna
- Context
- 1.05M
- 128K max output
- Input price
- $0.20
- per 1M tokens · OpenAI API
- Output price
- $1.20
- per 1M tokens
- Epoch Capabilities Index
- 156.3
- #21 of 71 listed
- LMArena Text
- 1,454
- #41 of 79 listed
Where to run it
3 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $0.20 / 1M tokens |
| Batch | $0.10 / 1M tokens | |
| Flex tier | $0.10 / 1M tokens | |
| Fast tier | $0.40 / 1M tokens | |
| Output | Standard | $1.20 / 1M tokens |
| Batch | $0.60 / 1M tokens | |
| Flex tier | $0.60 / 1M tokens | |
| Fast tier | $2.40 / 1M tokens | |
| Cache read | Standard | $0.020 / 1M tokens |
| Batch | $0.010 / 1M tokens | |
| Flex tier | $0.010 / 1M tokens | |
| Fast tier | $0.040 / 1M tokens | |
| Cache write | Standard | $0.25 / 1M tokens |
| Batch | $0.13 / 1M tokens | |
| Flex tier | $0.13 / 1M tokens | |
| Fast tier | $0.50 / 1M tokens | |
Azure OpenAI in Foundry (opens in a new tab) gpt-5-6-luna | ||
| Input | Standard | $0.20 / 1M tokens |
| Output | Standard | $1.20 / 1M tokens |
| Cache read | Standard | $0.020 / 1M tokens |
| Cache write | Standard | $0.25 / 1M tokens |
Azure OpenAI in Foundry (opens in a new tab) gpt-5-6-luna | ||
| Input | Standard | $0.22 / 1M tokens |
| Output | Standard | $1.32 / 1M tokens |
| Cache read | Standard | $0.030 / 1M tokens |
| Cache write | Standard | $0.28 / 1M tokens |
Changes
All changes →- 4 prices dropped on OpenAI API Input (Prompts over 272K tokens, Fast tier) $0.80 · Cache read (Prompts over 272K tokens, Fast tier) $0.080 · Cache write (Prompts over 272K tokens, Fast tier) $1.00 · Output (Prompts over 272K tokens, Fast tier) $3.60
Vendor-reported scores
Published by OpenAI, under the conditions it states| Benchmark | Setting | Score |
|---|---|---|
| SWE-bench Pro | — | 62.7% |
| DeepSWE 1.1 | — | 67.2% |
| Terminal-Bench 2.1 | single agent | 84.7% |
| OSWorld 2.0 | set and scoring not stated | 45.6% |
| BrowseComp | single agent | 83.3% |
| GPQA Diamond | — | 92.3% |
| MMMU-Pro | no tools | 78.4% |
| with tools | 79.5% | |
| MRCR v2 | 8-needle, 256K–512K | 41.3% |
| 8-needle, 512K–1M | 41.3% |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 156.3
#21 of 71 listed models · CI 153.6–158.9
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text 1,454
#41 of 79 listed models · xhigh effort · CI 1,450–1,459 · 35,823 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- Epoch AI · FrontierMath Tiers 1–3 82.1%
#10 of 56 listed models · max effort · ±2.27
Also listed: low effort 41.4% · reasoning off 39.6%
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · GPQA Diamond 91.6%
#18 of 64 listed models · max effort · ±1.73
Also listed: low effort 82.3% · reasoning off 63.6%
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text · Chinese 1,476
#52 of 79 listed models · xhigh effort · CI 1,464–1,488 · 2,848 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,501
#41 of 79 listed models · xhigh effort · CI 1,494–1,508 · 9,953 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,259
#32 of 49 listed models · xhigh effort · CI 1,250–1,267 · 7,793 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made