Hi everyone,
I got a mail from LiveKit saying our project used 80% of the free inference credits for this month.
Can someone explain what this limit actually is and which service is using it? Also, what will happen if the limit gets exceeded?
We are using LiveKit for voice assessment features in our project. Just wanted to understand the warning mail better.
Thanks!
You are on the build plan, so the actual limit is $2.50 in credits shared across all inference providers: https://livekit.com/pricing/inference#inference-credits
The best breakdown for which services you are actually using is Sign in | LiveKit Cloud, though that’s not realtime data so it might need a bit of interpretation which of your LLM, TTS or STT is the main contributor (likely all 3)
If you exceed your limit, because you are on build, you will start to see 429 error in your logs and the agent will no longer have access to the Inference models. The intention of this limit is to provide you enough capacity for development, then you are ready to launch, you can upgrade to ship with higher limits.