| ▲ | minimaxir 5 hours ago | |
The actual token calculations with input videos for Gemini 3 Pro is...confusing. | ||
| ▲ | pseudosavant 3 hours ago | parent [-] | |
That is because it isn't actually tokens that are fed into the model for non-text. For text, it is tokenized, and each token has a specific set of vectors. But with other media, they've trained encoders that analyze the media and produce a set of vectors that are the same "format" as the token's vectors, but it isn't actually ever a token. Most companies have rules for how many tokens the media should "cost", but they aren't usually exact. | ||