Gemini 3.8 Flash vs GPT-6 Luna
Gemini 3.8 Flash is from Google, released September 2, 2026. GPT-6 Luna is from OpenAI, released September 22, 2026.
- LMArena Elo1494 vs 1444. Gemini 3.8 Flash is 3.3% ahead on LMArena Elo.
- Input per 1M$0.75 vs $0.10. GPT-6 Luna costs 87% less per million input tokens.
- Output per 1M$3.75 vs $0.50. GPT-6 Luna costs 87% less per million output tokens.
- Context window1M vs 1,050,000. GPT-6 Luna takes 4.8% more context in one request.
Prices are the vendors’ published API rates; Elo is LMArena’s text board. Each figure is dated on its model page.
Interactive Comparison
Loading chart...
$0.75 / $3.75 per 1M tokens (introductory, to 31 Dec 2026) | $0.10 / $0.50 per 1M tokens | |
|---|---|---|
| Identity | ||
| Developer | OpenAI | |
| Released | Sep 2026 | Sep 2026 |
| Status | GA | GA |
| Licence | Proprietary | Proprietary |
| Self-hostable | No | No |
| Cost | ||
| Blended $/1M tokensinput × 0.75 + output × 0.25 | $1.500 / 1M tokens | $0.200 / 1M tokens |
| Input price | $0.750 / 1M tokens | $0.100 / 1M tokens |
| Output price | $3.750 / 1M tokens | $0.500 / 1M tokens |
| Cached input | — | $0.01 per 1M tokens |
| Batch discount | — | 50% (Batch and Flex) |
| Capacity | ||
| Context window | 1M tokens | 1,050,000 tokens |
| Max output | 64k tokens | 128k tokens |
| Long-context surcharge | — | Prompts over 272K input tokens: 2x input and cache rates, 1.5x output |
| Capability | ||
| Vision in | — | Yes |
| Audio in | — | No |
| Function calling | — | Yes |
| Structured output | — | Yes |
| Extended reasoning | Tunable thinking: low, medium (default), high. The "minimal" level is not supported. | Yes |
| Web search | — | Yes |
| Code execution | — | Yes |
| Access | ||
| API | Yes | Yes |
| Chat app | Yes | Yes |
| Fine-tuning | — | No |
| Measured quality | ||
| LMArena Elo | 1494 (checked Oct 2026) | 1444 (checked Oct 2026) |
| LMArena rank | Rank 11 | Rank 85 |
| GPQA Diamond | 95 | — |
| Elo per dollarLMArena Elo ÷ blended $/1M tokens | 996 | 7220 |
