What is the usual per-minute use cost of a realtim...
# ask-ai
i
What is the usual per-minute use cost of a realtime multimodal agent?
t
Thanks for reaching out, Matthew. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
I'm happy to share that the per-minute use cost of a realtime multimodal agent deployed on LiveKit Cloud is $0.01 per minute for active agent session time. This covers hosting your agent across LiveKit’s global network, unlimited data transfer, and access to helpful observability and analytics features to keep everything running smoothly. Just a quick note: this rate applies specifically to agents managed on LiveKit Cloud. If you choose to self-host agents using the open-source LiveKit Agents framework, the cost structure will be a bit different, based on your individual resource usage. Also, keep in mind that any costs for third-party AI services (like LLMs, STT, or TTS) are billed separately by those providers. Sources: Deploy and scale agents on LiveKit Cloud | Deploy and scale agents on LiveKit Cloud | Deploy and scale agents on LiveKit Cloud | LiveKit Pricing
i
How about OpenAI's realtime API?
t
Thank you for reaching out! I understand that the cost of using OpenAI's realtime API can be a bit unclear since it's not detailed in LiveKit's documentation. To get the most accurate and up-to-date pricing information, I recommend checking out OpenAI's official pricing page or getting in touch with their support team. If you need any help navigating that, I'm here for you! Sources: Russ d'Sa - LiveKit Blog | Russ d'Sa - LiveKit Blog | OpenAI Realtime API integration guide | LiveKit Docs | OpenAI Realtime API integration guide | LiveKit Docs | plugins/openai/src/realtime/api_proto.ts