Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of Nemotron-3.5-ASR-Streaming-Multilingual-0.6b, Nemotron-3-Diarization
2 modelsnvidiaNemotron-3.5-ASR-Streaming-Multilingual-0.6bRemove ×nvidiaNemotron-3-DiarizationRemove ×
What’s differentNemotron 3.5 ASR Streaming Multilingual is an open 0.6B-parameter prompt-conditioned cache-aware FastConformer-RNNT model, engineered for low-latency streaming transcription across 40+ languages. It powers…Nemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call…
DateJun 3, 2026ListedSep 25, 2026Listed
Listed rate$3.33 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗$0.00001/ secondDeepInfra · all routes ↗Input audio second
Provider endpoints2 endpoints →1 endpoint →
Context window——
Max output——
Parameters0.6B—
Audio inputSupportedNot reported
Open weightsSupportedNot reported

Add another model

Search all models →