Artificial Analysis(@ArtificialAnlys):To measure speed and cost efficiency, we benchmarked Nemotron 3.5 Transcribe on DeepInfra's hosted endpoint. On DeepInfra, it reaches a Speed Factor of 75x, transcribing 1 minute of audio in under 1 second, and costs $2.00 per 1,000 minutes of audio.

Artificial Analysis

@ArtificialAnlys

Independent analysis of AI

Joined January 2024

693 Following 178.4K Followers

Artificial Analysis@ArtificialAnlys

2026.10.28 15:05

To measure speed and cost efficiency, we benchmarked Nemotron 3.5 Transcribe on DeepInfra's hosted endpoint. On DeepInfra, it reaches a Speed Factor of 75x, transcribing 1 minute of audio in under 1 second, and costs $2.00 per 1,000 minutes of audio.