Skip to main content

Plans designed to scale with your projects

From building your first AI voice or video agent to realtime applications with millions of users and everything in between.

Build
Everything you need to start a project.
Start for free

No credit card required
$0/mo

Start with:
Agent deployment
Agent observability
Inference credits
Global edge network
Telephony (1 free number)
Session metrics and analytics
Community support
Ship
For shipping your project to real users.
Start building

STARTING AT
$50/mo

Everything in Build, plus:
Team collaboration
Instant rollback to a previous agent deployment
Email support
Scale
For scaling applications and global reach.
Start building

STARTING AT
$500/mo

Everything in Ship, plus:
Role-based access
Metrics export APIs
Region pinning
Security reports / HIPAA
Enterprise
For teams interested in the white-glove treatment.
Contact sales

Custom

Everything in Scale, plus:
Volume pricing
Slack
Shared Slack channel
SSO
Support SLA
Pricing Calculator

Estimate costs for
AI voice and video agents

Preview the per-minute cost to run an agent on LiveKit Cloud. Our plans include monthly allotments for agent session minutes, inbound calling minutes (for US local phone numbers), and inference credits to call the most popular AI models. For a complete list of supported providers and models, see Documentation.

How users connect to your agent
Agent session
$0.0100/min
Telephony
--
WebRTC Connection
Connection and data transfer
--
LLM(Large language model)
--
STT(Speech-to-text)
--
TTS(Text-to-speech)
--
Total
estimated cost
$0.0100/min

Frequently asked questions

Can I self-host LiveKit?

Both LiveKit’s media server and LiveKit’s Agents framework are completely open source and available to host on your own infrastructure. View the docs to get started.

Do you offer on-premise or private deployments?

Yes. Contact sales so we can better understand your needs.

What’s the difference between agents deployed on LiveKit Cloud and self-hosted agents built with LiveKit’s Agents framework?

An agent deployed on LiveKit Cloud is fully managed in the cloud and billed by the number of agent session minutes. Self-hosted agents built with LiveKit’s Agents framework can use LiveKit’s global edge network for realtime media transport, which is billed by individual resource usage.

Agents deployed
on LiveKit Cloud
Self-hosted agents
Downstream data transfer from server to agentBilled per GBBilled per GB
Participant minuteBilled as either a WebRTC or SIP minuteBilled as either a WebRTC or SIP minute
Downstream data transfer from server to participantBilled per GBBilled per GB
Detailed agent observabilityBilled per minute of audio recording and per observability eventBilled per minute of audio recording and per observability event
Powering billions of calls in production for:
Open AI
Speak AI
xAI
Character AI
Hello Patient

Ready to build?

Start building your realtime application with a free account. Reach out to us if you're interested in custom pricing.

No credit card required • 1,000 free agent session minutes monthly