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

Inference discounts

Enterprise

For teams interested in the white-glove treatment.

Contact sales

Custom

Everything in Scale, plus:

Volume pricing, including inference

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 detailed LLM, STT, and TTS model pricing, see Inference pricing.

For detailed provider and model API support, see Documentation.

How users connect to your agent

Select a plan

Agent session

$0.0100/min

Telephony

$0.0100/min

WebRTC Connection

Connection and data transfer

LLM

$0.0015/min

STT

$0.0092/min

TTS

$0.0300/min

Observability

$0.0100/min

Total
estimated cost

$0.0707/min

LLM model prices (per minute)

DeepSeek DeepSeek-V3: $0.0024/min
Google Gemini 2.5 Flash: $0.0013/min
Google Gemini 2.5 Flash-Lite: $0.0004/min
Google Gemini 2.5 Pro: $0.0101/min
Google Gemini 3 Flash: $0.0020/min
Google Gemini 3.1 Flash Lite: $0.0010/min
Google Gemini 3.1 Pro: $0.0152/min
Moonshot AI Kimi K2.5: $0.0023/min
OpenAI GPT-4.1: $0.0074/min
OpenAI GPT-4.1 mini: $0.0015/min
OpenAI GPT-4.1 nano: $0.0004/min
OpenAI GPT-4o: $0.0093/min
OpenAI GPT-4o mini: $0.0006/min
OpenAI GPT-5: $0.0055/min
OpenAI GPT-5 mini: $0.0011/min
OpenAI GPT-5 nano: $0.0002/min
OpenAI GPT-5.1: $0.0055/min
OpenAI GPT-5.1: $0.0055/min
OpenAI GPT-5.2: $0.0077/min
OpenAI GPT-5.2 Chat: $0.0077/min
OpenAI GPT-5.3 Chat: $0.0077/min
OpenAI GPT-5.4: $0.0189/min
OpenAI GPT OSS 120B: $0.0006/min
Qwen Qwen3 235B-A22B Instruct: $0.0008/min
OpenAI GPT Realtime: $0.0676/min
OpenAI GPT Realtime mini: $0.0216/min
Gemini Live 2.5 Flash Native Audio: $0.0144/min
Gemini Live 2.5 Flash: $0.0144/min

STT model prices — Build/Ship plan (per minute)

AssemblyAI Universal-3 Pro Streaming: $0.0075/min
AssemblyAI Universal-Streaming: $0.0025/min
AssemblyAI Universal-Streaming-Multilingual: $0.0025/min
Cartesia Ink Whisper: $0.0030/min
Deepgram Flux: $0.0077/min
Deepgram Nova-2: $0.0058/min
Deepgram Nova-2 Conversational AI: $0.0058/min
Deepgram Nova-2 Medical: $0.0058/min
Deepgram Nova-2 Phone Call: $0.0058/min
Deepgram Nova-3 (Monolingual): $0.0077/min
Deepgram Nova-3 Medical: $0.0077/min
Deepgram Nova-3 (Multilingual): $0.0092/min
ElevenLabs Scribe v2 Realtime: $0.0105/min

STT model prices — Scale plan (per minute)

AssemblyAI Universal-3 Pro Streaming: $0.0075/min
AssemblyAI Universal-Streaming: $0.0025/min
AssemblyAI Universal-Streaming-Multilingual: $0.0025/min
Cartesia Ink Whisper: $0.0023/min
Deepgram Flux: $0.0065/min
Deepgram Nova-2: $0.0047/min
Deepgram Nova-2 Conversational AI: $0.0047/min
Deepgram Nova-2 Medical: $0.0047/min
Deepgram Nova-2 Phone Call: $0.0047/min
Deepgram Nova-3 (Monolingual): $0.0065/min
Deepgram Nova-3 Medical: $0.0065/min
Deepgram Nova-3 (Multilingual): $0.0078/min
ElevenLabs Scribe v2 Realtime: $0.0105/min

TTS model prices — Build/Ship plan (per minute)

Cartesia Sonic: $0.0300/min
Cartesia Sonic 2: $0.0300/min
Cartesia Sonic 3: $0.0300/min
Cartesia Sonic 3 (2025-10-27): $0.0300/min
Cartesia Sonic 3 (2026-01-12): $0.0300/min
Cartesia Sonic Turbo: $0.0300/min
Deepgram Aura-2: $0.0180/min
ElevenLabs Eleven Flash v2: $0.0900/min
ElevenLabs Eleven Flash v2.5: $0.0900/min
ElevenLabs Eleven Multilingual v2: $0.1800/min
ElevenLabs Eleven Turbo v2: $0.0900/min
ElevenLabs Eleven Turbo v2.5: $0.0900/min
Inworld Inworld TTS 1: $0.0030/min
Inworld Inworld TTS 1 Max: $0.0060/min
Inworld Inworld TTS 1.5 Max: $0.0060/min
Inworld Inworld TTS 1.5 Mini: $0.0030/min
Rime Arcana: $0.0240/min
Rime Mist: $0.0180/min
Rime Mist v2: $0.0180/min
xAI Text to Speech: $0.0025/min

TTS model prices — Scale plan (per minute)

Cartesia Sonic: $0.0225/min
Cartesia Sonic 2: $0.0225/min
Cartesia Sonic 3: $0.0225/min
Cartesia Sonic 3 (2025-10-27): $0.0225/min
Cartesia Sonic 3 (2026-01-12): $0.0225/min
Cartesia Sonic Turbo: $0.0225/min
Deepgram Aura-2: $0.0162/min
ElevenLabs Eleven Flash v2: $0.0360/min
ElevenLabs Eleven Flash v2.5: $0.0360/min
ElevenLabs Eleven Multilingual v2: $0.0720/min
ElevenLabs Eleven Turbo v2: $0.0360/min
ElevenLabs Eleven Turbo v2.5: $0.0360/min
Inworld Inworld TTS 1: $0.0030/min
Inworld Inworld TTS 1 Max: $0.0060/min
Inworld Inworld TTS 1.5 Max: $0.0060/min
Inworld Inworld TTS 1.5 Mini: $0.0030/min
Rime Arcana: $0.0180/min
Rime Mist: $0.0120/min
Rime Mist v2: $0.0120/min
xAI Text to Speech: $0.0025/min

Build

$0/mo

Start for free

Ship

$50/mo

Start building

Scale

$500/mo

Start building

Enterprise

Custom

Contact sales

AI voice and video agents

Deploy and host agents on LiveKit Cloud infrastructure

Agent session minutes

Time spent in a session by an agent deployed on LiveKit Cloud

1,000 minutes included

5,000 minutes included

then $0.01 per min

50,000 minutes included

then $0.01 per min

Custom

Concurrent agent sessions

Number of concurrent sessions across all agents deployed on LiveKit Cloud

Up to 600

Starts at 50, request more via dashboard

Custom

Agent deployments

Number of agents deployed on LiveKit Cloud

Custom

Deployment metrics

View resource allocation, latency, errors, and process metrics

Cold start prevention

Keep agents always-on for instant responses

—

Instant rollback

Revert a deployment back to a previous version

—

Audio enhancement

Improve STT accuracy and VAD precision

Speaker isolation

Elevate the foreground speaker while suppressing background voices with ai-coustics' Voice Focus model

100 minutes included

1,000 minutes included

then $0.0012/min

10,000 minutes included

then $0.0012/min

Custom

Conversational intelligence

Built-in models for end-of-turn detection and interruption handling

LiveKit Inference

Access LLM, STT, and TTS models with a single API key

Inference pricing

LiveKit Inference credits

Call popular models with LiveKit's inference service

$2.50 in credits

~50 minutes, based on model prices

$5 in credits

~100 minutes, then billed based on model prices

$50 in credits

~1,000 minutes, then billed based on discounted model prices

Custom

LiveKit Inference concurrency

Number of concurrent sessions connected to LiveKit's inference service

Request more via dashboard

Custom

Agent observability

Gather insights into your agent's behavior and performance

Agent session recordings

Download and play back audio from recorded agent sessions

1,000 minutes included

5,000 minutes included

then $0.005 per min

50,000 minutes included

then $0.005 per min

Custom

Agent observability events

Review turn-by-turn details for recorded agent sessions, including transcripts, trace spans, and logs

100,000 entries included

500,000 entries included

then $0.00003 per entry

5,000,000 entries included

then $0.00003 per entry

Custom

Export to cloud storage

Send session recordings, transcripts, traces, and logs to cloud storage

—

Coming soon

Telephony

Connect with your users over regular phone calls

US local phone numbers

Monthly rental of a US local phone number

1 free number

then $1.00/month per number

1 free number

then $1.00/month per number

Custom

US local inbound minutes

Inbound minutes to a US local number

50 minutes included

100 minutes included

then $0.01 per min

1,000 minutes included

then $0.01 per min

Custom

US toll-free phone numbers

Monthly rental of a US toll-free phone number

—

$2.00/month per number

Custom

US toll-free inbound minutes

Inbound minutes to a US toll-free number

—

$0.02 per minute

Custom

Third-party SIP minutes

Inbound and outbound minutes using a third-party SIP trunk

1,000 minutes included

5,000 minutes included

then $0.004 per min

50,000 minutes included

then $0.003 per min

Custom

Custom SIP domains

Use your own domain for inbound SIP endpoints instead of livekit.cloud

—

Participants

Allow end users to connect to realtime sessions

WebRTC minutes

Time an end user spends connected to our network via WebRTC

5,000 minutes included

150,000 minutes included

then $0.0005 per min

1.5M minutes included

then $0.0004 per min

Custom

Concurrent connections

Number of end users and agents connected to our network

100

1,000

5,000

Custom

Media transport

Deliver voice and video worldwide in under 250ms

Uptime

Global availability of LiveKit's realtime network

99.99%

Enhanced noise cancellation

Automatic background noise reduction for voice streams with Krisp

Downstream data transfer

Data transfer from our network to participants

50GB included

250GB included

then $0.12 per GB

3TB included

then $0.10 per GB

Custom

Stream import

Ingest media encoded in another format and deliver it as a realtime stream

Transcode minutes

Time spent converting media from source format to RTP.

Transcode-less imports (e.g., WHIP without transcode) are free.

60 minutes included, shared with recording and export

600 minutes included, shared with recording and export

then $0.02 per minute (video) then $0.005 per minute (audio-only)

8,000 minutes included, shared with recording and export

then $0.015 per minute (video) then $0.004 per minute (audio-only)

Custom

Concurrent imports

Number of Ingresses running concurrently

100

500

Custom

Recording and export

Capture realtime media and encode it in another format for recording or multistreaming

Transcode minutes

Time spent running RoomComposite and Participant Egresses.

Supports multiple export destinations per target format.

60 minutes included, shared with stream import

600 minutes included, shared with stream import

then $0.02 per minute (video) then $0.005 per minute (audio-only)

8,000 minutes included, shared with stream import

then $0.015 per minute (video) then $0.004 per minute (audio-only)

Custom

Track egress

Raw single stream exports

60 minutes included

600 minutes included

then $0.001 per minute

8,000 minutes included

then $0.001 per minute

Custom

Concurrent exports

Number of Egresses running concurrently

100

500

Custom

Platform

Build, ship, and manage your applications with additional tools and features

Dashboard

View sessions and detailed usage metrics, spin up sandboxes, and manage project settings

CLI

Manage and interact with your application from the command line

Team collaboration

Build applications together with your team

—

Metrics export APIs

Query and export analytics or telemetry data to external systems

—

Shared plan across projects

Share a single plan across multiple projects for unified billing

—

Non-credit card billing

Alternative payment options including invoicing and wire transfers

—

Security and compliance

Protect your applications through access, application, and operational security

End-to-end encryption

Fully encrypt streams between sender and receiving clients

DPA

Data processing addendum

Standard

Custom

Role-based access

Assign different roles and capabilities to project collaborators

—

Region pinning

Restrict which data center regions may route or process media streams

—

Security reports

Access third-party audit reports of our network infrastructure and operational security

—

Includes: SOC 2 Type II, Network pentest

HIPAA compliance

Signed BAA

—

Single sign-on (SSO)

Authenticate with your enterprise identity

—

AWS Assume Role for S3 egress

Use IAM roles with temporary credentials for S3 exports instead of long-lived access keys

—

Support

Get help and technical assistance for building your applications

Community support

Help and advice for building your application from the LiveKit community

Email support

Reach out to the LiveKit team for help via email

—

Shared Slack channel

Build and collaborate with the LiveKit team in a private Slack channel

—

Designated solutions engineer

A specific LiveKit team member focused on helping you build your application

—

Support SLA

Escalation privileges and guaranteed response times for support tickets

—

FAQs

What's the difference between agent deployments, concurrent agent sessions, and LiveKit Inference concurrency?

An agent deployment is a running version of your agent backend hosted on LiveKit Cloud, typically with a unique prompt, set of voice AI models, and function calls. You can configure your agent to complete different tasks or workflows. Deploy separate agents when you need distinct reasoning behavior or tool access (e.g., a front-office receptionist agent to handle inbound phone calls for appointment scheduling and triage vs a back-office agent to make outbound calls to insurance providers to verify patient coverage).

A concurrent agent session is a live interaction between your agent and an end user. If your agent is handling 10 calls or conversations at the same time, that counts as 10 concurrent sessions, regardless of how many agent deployments you have on LiveKit Cloud.

LiveKit Inference concurrency refers specifically to how many AI inference requests across LLM, STT, and TTS can run at the same time through LiveKit Inference. It limits how many model calls can be processed concurrently, independent of how many agent sessions or deployments you have. The LiveKit Inference concurrency limit for each plan applies to your aggregate usage of a model type (e.g., total connections to any LiveKit Inference STT). For example, if there are 10 concurrent agent sessions running and the agent is configured to use LiveKit Inference for STT, then there are 10 concurrent STT connections.

For more information on LiveKit Cloud quotas and limits, refer to our docs.

Can I self-host LiveKit?

The LiveKit Agents framework and LiveKit media server are both completely open source and available to run locally or host on your own infrastructure.

LiveKit Cloud is the best way to run LiveKit in production, with fully managed agent deployments, built-in observability and dashboards, and ultra low-latency global media transport.

Sign up for LiveKit Cloud here, or refer to our docs on how to run LiveKit's media server locally or deploy LiveKit Agents in a custom environment.

Do you offer on-premise or private deployments?

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

Powering billions of calls in production for:

Ready to build?

Start building a voice AI agent with a free account. Reach out to us if you're interested in custom pricing.

Start building

Contact sales

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

Plans designed to scale with your projects

Estimate costs forAI voice and video agents

LLM model prices (per minute)

STT model prices — Build/Ship plan (per minute)

STT model prices — Scale plan (per minute)

TTS model prices — Build/Ship plan (per minute)

TTS model prices — Scale plan (per minute)

Build

Ship

Scale

Enterprise

AI voice and video agents

Agent session minutes

Concurrent agent sessions

Agent deployments

Deployment metrics

Cold start prevention

Instant rollback

Audio enhancement

Speaker isolation

Conversational intelligence

LiveKit Inference

LiveKit Inference credits

LiveKit Inference concurrency

Agent observability

Agent session recordings

Agent observability events

Export to cloud storage

Telephony

US local phone numbers

US local inbound minutes

US toll-free phone numbers

US toll-free inbound minutes

Third-party SIP minutes

Custom SIP domains

Participants

WebRTC minutes

Concurrent connections

Media transport

Uptime

Enhanced noise cancellation

Downstream data transfer

Stream import

Transcode minutes

Concurrent imports

Recording and export

Transcode minutes

Track egress

Concurrent exports

Platform

Dashboard

CLI

Team collaboration

Metrics export APIs

Shared plan across projects

Non-credit card billing

Security and compliance

End-to-end encryption

DPA

Role-based access

Region pinning

Security reports

HIPAA compliance

Single sign-on (SSO)

AWS Assume Role for S3 egress

Support

Community support

Email support

Shared Slack channel

Designated solutions engineer

Support SLA

FAQs

Ready to build?

Estimate costs for
AI voice and video agents