LiveKit Inference cuts GPT-5.6 Luna and Terra per-minute rates
LiveKit's per-minute LLM pricing dropped for two existing GPT-5.6 Inference SKUs: Luna fell 80% to $0.0008/min and Terra fell 20% to $0.0081/min, while Sol held at $0.0203/min and all LiveKit Cloud plan prices stayed unchanged.
GPT-5.6 Luna $0.0040/min, GPT-5.6 Terra $0.0101/min, GPT-5.6 Sol $0.0203/min (as of 2026-07-21)
GPT-5.6 Luna $0.0008/min, GPT-5.6 Terra $0.0081/min, GPT-5.6 Sol $0.0203/min unchanged (as of 2026-08-11)
LiveKit quietly repriced two of the three GPT-5.6 SKUs it added to LiveKit Inference back on 2026-07-21. GPT-5.6 Luna, the cheapest of the three, dropped from $0.0040/min to $0.0008/min — an 80% cut — and GPT-5.6 Terra fell from $0.0101/min to $0.0081/min, a 20% cut. GPT-5.6 Sol, the priciest of the trio, held at $0.0203/min.
This is a genuine per-SKU repricing rather than the calculator-default swap LiveKit used in July to move its advertised blended rate: the pricing page’s default voice-agent estimate still reads $0.0672/min because that calculation runs on Gemma 4 31B, which wasn’t among the repriced models. No LiveKit Cloud plan price, allotment or overage rate moved — Build stays free, Ship $50/mo, Scale $500/mo, Enterprise custom.
Plan structure holds (Build free / Ship $50 / Scale $500 / Enterprise custom). Two existing LiveKit Inference LLM SKUs get cheaper: GPT-5.6 Luna falls from $0.0040/min to $0.0008/min (-80%) and GPT-5.6 Terra falls from $0.0101/min to $0.0081/min (-20%); GPT-5.6 Sol holds at $0.0203/min.