← All comparisons
Gemini 3.8 Flash vs GPT 5.6 Luna
Side-by-side comparison of token prices, context windows, and capabilities across official model makers.
| Specification | Gemini 3.8 Flash gemini-3.8-flash | GPT 5.6 Luna gpt-5.6-luna |
|---|---|---|
| Official provider | OpenAI | |
| Input / 1M | $1.50$0.525save $0.975 | $0.20$0.07save $0.13 Cheaper |
| Output / 1M | $7.50$2.625save $4.875 | $1.20$0.42save $0.78 Cheaper |
| Context | 1.05M | 1.05M |
| Max out | 65.5K | 128K |
| Capabilities | visiontoolsreasoningcache | visiontoolsreasoningcache |
30-day workload (30M input · 80% cached · 3M output) Estimated monthly spend on AivoKey | $23.625 | $3.36 |
| Model details | Gemini 3.8 Flash → | GPT 5.6 Luna → |