Google: Gemini 3.8 Flash vs Macaron V1 Venti
Google: Gemini 3.8 Flash is 1.1× cheaper for input tokens: Google: Gemini 3.8 Flash costs $0.75 per M and Macaron V1 Venti costs $0.825 per M. Macaron V1 Venti is 1.5× cheaper for output tokens: Google: Gemini 3.8 Flash costs $3.75 per M and Macaron V1 Venti costs $2.475 per M. Both read up to 1,048,576 tokens of context. Google: Gemini 3.8 Flash accepts audio, file, image, text, video; Macaron V1 Venti accepts text.
| Google: Gemini 3.8 Flash | Macaron V1 Venti | |
|---|---|---|
| Model id | google/gemini-3.8-flash | mindai/macaron-v1-venti |
| Input | $0.75 per M | $0.825 per M |
| Output | $3.75 per M | $2.475 per M |
| Context length | 1,048,576 tokens | 1,048,576 tokens |
| Accepts | audio, file, image, text, video | text |
| Produces | text | text |
| Served by | novita |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.