GPT-6 Luna
OpenAIProprietaryReleased Sep 22, 2026
GPT-6 Luna ranks #164 on LMArena (1391.1); official output price $0.50 per 1M tokens.
Key metrics
Rank history
LMArena rank, last 14 days#158 on Sep 26, #164 now; best #158 in this period.
Reasoning effort comparison
Artificial Analysis measurements per reasoning effort of the same model| Effort | Intelligence | Coding | tok/s | TTFT (s) | First answer (s) |
|---|---|---|---|---|---|
| maxUsed in table | 38.1 | – | 135 | 103 | 103 |
| xhigh | 34.6 | – | 132 | 30 | 30 |
| high | 32.9 | – | 123 | 17 | 17 |
| medium | 29.9 | – | – | – | – |
| low | 21.5 | – | 120 | 3.3 | 3.3 |
| non-reasoning | 18.5 | – | 119 | 0.9 | 0.9 |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 65 | 1412.8 | 15.6 | $6.00 | – | |
| 66 | 1399.3 | 46.4 | $6.00 | 70 | |
| 67 | 1395.0 | 47.6 | $10.00 | – | |
| 68 | 1391.1 | 38.1 | $0.50 | 135 |
More from OpenAI
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 22 | 1471.5 | 38.4 | $30.00 | – | |
| 27 | 1469.0 | 39.0 | $15.00 | – | |
| 35 | 1457.3 | 47.0 | $20.00 | – | |
| 44 | 1446.5 | 42.1 | $12.00 | 111 | |
| 45 | 1446.5 | 51.8 | $10.00 | 58 | |
| 48 | 1442.7 | 24.7 | $10.00 | – |
Pricing
- Official API list price: $0.10 input and $0.50 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $0.20 per 1M tokens.
- Among 78 models with an output price, it is the #5 cheapest.
- The cheapest OpenRouter route charges $0.10 input / $0.50 output.
Sources & methodology
GPT-6 Luna (OpenAI): Arena 1391.1 (#164), Intelligence Index 38.1, $0.10 in / $0.50 out per 1M tokens, 1.05M context. Data updated Oct 9, 2026.
- LMArena — Arena score, 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
FAQ
What rank is GPT-6 Luna right now?
GPT-6 Luna is #68 on our leaderboard of 68 scored models (Arena score 1391.1); its raw LMArena rank is #164.
What does GPT-6 Luna cost via API?
Input $0.10 / output $0.50 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $0.20 per 1M tokens.
How fast is GPT-6 Luna?
Artificial Analysis measures about 135 output tokens per second, 103 s to the first token and 103 s to the first answer token; it is a reasoning model, so latency includes thinking time.
Is GPT-6 Luna open source? Can it be self-hosted?
GPT-6 Luna is a closed model, available only via official APIs or hosted services.
What is the context length of GPT-6 Luna?
1.05M (1,050,000 tokens, as listed on OpenRouter).