Thanks — I’m following up about where to find the standard model prices for inference usage.
You can view LiveKit’s full pay-as-you-go inference pricing on the LiveKit Inference pricing page:
•
https://livekit.io/pricing/inference
That page lists pricing for:
• LLMs (per-million-token rates for input/output and cached input)
• STT (per-minute rates by provider/model)
• TTS (per-million-characters rates by provider/model)
If you’d like, I can pull the specific TTS, STT, or LLM model prices you care about (or compare costs between a couple of providers/models). Which models or providers do you want details for?
Sources:
Build voice, video, and physical AI | LiveKit