Skip to main content
TC
TokenCost

LLM Models with Audio Input

Models that can process audio files, voice recordings, and speech directly. 3 models available.

ModelProviderInput /1MOutput /1M
Gemini 3 FlashGoogle$0.500$3.00
Gemini 3.1 ProGoogle$2.00$12.00
Gemini 3 ProGoogle$2.00$12.00