Side by side

See the difference.

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

Scroll to compare models →

Comparison of glm-5.2-fast, Nemotron-3-Diarization
2 modelsUnknownglm-5.2-fastRemove ×nvidiaNemotron-3-DiarizationRemove ×
What’s differentTool calling · Structured outputNemotron 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…
DateOct 16, 2026DiscoveredSep 25, 2026Listed
Listed rate$2.31 in / $7.26 out/ 1M tokensExperiential · all routes ↗Standard list rate$0.00001/ secondDeepInfra · all routes ↗Input audio second
Provider endpoints1 endpoint →1 endpoint →
Context window——
Max output——
Parameters——
Tool callingSupportedNot reported
Structured outputSupportedNot reported
ReasoningSupportedNot reported

Add another model

Search all models →