All AI models · LLM benchmarks · Methodology

Active Speaker Detection

Nemotron multimodal model for visual reasoning and agentic AI workflows

Model facts

Context window
not published tokens
Maximum output
4K tokens
Cheapest paid input
free per 1M tokens
Cheapest paid output
free per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

attachments, open weights, video.

Observed price history

  • 2026-08-24: free input / free output per 1M tokens

API providers

  • Nvidia — model id nvidia/active-speaker-detection; free input / free output per 1M tokens; provider documentation