theserverless.dev InferenceList

Models

Showing 1–3 of 3 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
MiniMax: H3 MiniMax text image video audio Not published— Not published— —
MiniMax: Speech 2.8 HD
Cheaper on fal (−99.9%)
MiniMax text audio Not published— Not published— —
MiniMax: Speech 2.8 Turbo MiniMax text audio Not published— Not published— —

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.