How GPT-5.6 Luna and Gemini 3.5 Flash Lite compare on price, context window, capabilities and plan. Use either one in Araveil, or leave it on Auto and Araveil picks one to suit each message.
Fast, ultra-affordable GPT-5.6 for high-volume everyday tasks
New messages will use it instead of Auto.
The cheapest Flash, built for volume rather than depth
New messages will use it instead of Auto.
Prices are each provider’s list price.
| GPT-5.6 Luna | Gemini 3.5 Flash Lite | |
|---|---|---|
| Provider | OpenAI | |
| Type | Text | Text |
| Plan | Free | Free |
| Input price | $0.20 per 1M tokens | $0.30 per 1M tokens |
| Output price | $1.20 per 1M tokens | $2.50 per 1M tokens |
| Reads up to | 922K tokens | 1.0M tokens |
| Writes up to | 128K tokens | 66K tokens |
| Speed | Fast | Fast |
| Vision | ||
| Audio | ||
| Web search | ||
| Thinking | ||
| Functions |
Not sure? Leave Araveil on Auto and every message goes to the model most likely to answer it best, so you never have to choose.