MiniMaxAI/MiniMax-M3 vs Google: Gemini 3.6 Flash
MiniMaxAI/MiniMax-M3 is 1.3× cheaper for input tokens: MiniMaxAI/MiniMax-M3 costs $0.60 per M and Google: Gemini 3.6 Flash costs $0.75 per M. MiniMaxAI/MiniMax-M3 is 1.6× cheaper for output tokens: MiniMaxAI/MiniMax-M3 costs $2.40 per M and Google: Gemini 3.6 Flash costs $3.75 per M. Both read up to 1,048,576 tokens of context. MiniMaxAI/MiniMax-M3 accepts text; Google: Gemini 3.6 Flash accepts audio, file, image, text, video.
| MiniMaxAI/MiniMax-M3 | Google: Gemini 3.6 Flash | |
|---|---|---|
| Model id | MiniMaxAI/MiniMax-M3 | google/gemini-3.6-flash |
| Input | $0.60 per M | $0.75 per M |
| Output | $2.40 per M | $3.75 per M |
| Context length | 1,048,576 tokens | 1,048,576 tokens |
| Accepts | text | audio, file, image, text, video |
| Produces | text | text |
| Served by | sambanova |
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.