# LiveKit Cloud Plans

## Build

**Price:** $0/mo
**Note:** No credit card required

Everything you need to start a project.

Start with:
- Agent deployment
- Agent observability
- Inference credits
- Global edge network
- Telephony (1 free number)
- Session metrics and analytics
- Community support

## Ship

**Price:** $50/mo
**Note:** STARTING AT

For shipping your project to real users.

Everything in Build, plus:
- Team collaboration
- Instant rollback to a previous agent deployment
- Email support

## Scale

**Price:** $500/mo
**Note:** STARTING AT

For scaling applications and global reach.

Everything in Ship, plus:
- Role-based access
- Metrics export APIs
- Region pinning
- Security reports / HIPAA
- Inference discounts

## Enterprise

**Price:** Custom

For teams interested in the white-glove treatment.

Everything in Scale, plus:
- Volume pricing, including inference
- Shared Slack channel
- SSO
- Support SLA


# LiveKit Cloud Feature Matrix

## AI voice and video agents

Deploy and host agents on LiveKit Cloud infrastructure

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| Agent session minutes | 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 | 5 | 20 | Up to 600 (Starts at 50, request more via dashboard) | Custom |
| Agent deployments | 1 | 2 | 4 | Custom |
| Deployment metrics | Yes | Yes | Yes | Yes |
| Cold start prevention | No | Yes | Yes | Yes |
| Instant rollback | No | Yes | Yes | Yes |
| Background noise suppression | Yes | Yes | Yes | Yes |
| Voice isolation | 100 minutes included | 1,000 minutes included (then $0.0012/min) | 10,000 minutes included (then $0.0012/min) | Custom |
| Conversational intelligence | Yes | Yes | Yes | Yes |

## LiveKit Inference

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

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| LiveKit Inference credits | $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 | 5 | 20 (Request more via dashboard) | 50 (Request more via dashboard) | Custom |

## Agent observability

Gather insights into your agent's behavior and performance

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| Agent session recordings | 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 | 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 | No | Coming soon | Coming soon | Coming soon |

## Telephony

Connect with your users over regular phone calls

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| US local phone numbers | 1 free number | 1 free number (then $1.00/month per number) | 1 free number (then $1.00/month per number) | Custom |
| US local inbound minutes | 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 | No | $2.00/month per number | $2.00/month per number | Custom |
| US toll-free inbound minutes | No | $0.02 per minute | $0.02 per minute | Custom |
| Third-party SIP minutes | 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 | No | No | No | Yes |

## Participants

Allow end users to connect to realtime sessions

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| WebRTC minutes (Self-hosted agents count against WebRTC participant minutes.) | 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 | 100 | 1,000 | 5,000 | Custom |

## Media transport

Deliver voice and video worldwide in under 250ms

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| Uptime | 99.99% | 99.99% | 99.99% | 99.99% |
| Enhanced noise cancellation | Yes | Yes | Yes | Yes |
| Downstream data transfer | 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

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| Transcode minutes (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 | 2 | 100 | 500 | Custom |

## Recording and export

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

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| Transcode minutes (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 | 60 minutes included | 600 minutes included (then $0.001 per minute) | 8,000 minutes included (then $0.001 per minute) | Custom |
| Concurrent exports | 2 | 100 | 500 | Custom |

## Platform

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

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| Dashboard | Yes | Yes | Yes | Yes |
| CLI | Yes | Yes | Yes | Yes |
| Team collaboration | No | Yes | Yes | Yes |
| Metrics export APIs | No | No | Yes | Yes |
| Shared plan across projects | No | No | No | Yes |
| Non-credit card billing | No | No | No | Yes |

## Security and compliance

Protect your applications through access, application, and operational security

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| End-to-end encryption | Yes | Yes | Yes | Yes |
| DPA | Standard | Standard | Standard | Custom |
| Role-based access | No | No | Yes | Yes |
| Region pinning | No | No | Yes | Yes |
| Security reports | No | No | Includes: SOC 2 Type II, Network pentest | Includes: SOC 2 Type II, Network pentest |
| HIPAA compliance | No | No | Yes | Yes |
| Single sign-on (SSO) | No | No | No | Yes |
| AWS Assume Role for S3 egress | No | No | No | Yes |

## Support

Get help and technical assistance for building your applications

| Feature | Build | Ship | Scale | Enterprise |
|---------|-------|------|-------|------------|
| Community support | Yes | Yes | Yes | Yes |
| Email support | No | Yes | Yes | Yes |
| Shared Slack channel | No | No | No | Yes |
| Designated solutions engineer | No | No | No | Yes |
| Support SLA | No | No | No | Yes |


# LiveKit Inference Model Pricing

## Speech-to-Text (STT)

| Model | Creator | Build (per min) | Ship (per min) | Scale (per min) |
|-------|---------|-----------------|----------------|-----------------|
| Universal-3 Pro Streaming | AssemblyAI | $0.0075 | $0.0075 | $0.0075 |
| Universal-Streaming | AssemblyAI | $0.0025 | $0.0025 | $0.0025 |
| Universal-Streaming-Multilingual | AssemblyAI | $0.0025 | $0.0025 | $0.0025 |
| Ink Whisper | Cartesia | $0.003 | $0.003 | $0.0023 |
| Flux | Deepgram | $0.0077 | $0.0077 | $0.0065 |
| Flux (Multilingual) | Deepgram | $0.0077 | $0.0077 | $0.0065 |
| Nova-2 | Deepgram | $0.0058 | $0.0058 | $0.0047 |
| Nova-2 Conversational AI | Deepgram | $0.0058 | $0.0058 | $0.0047 |
| Nova-2 Medical | Deepgram | $0.0058 | $0.0058 | $0.0047 |
| Nova-2 Phone Call | Deepgram | $0.0058 | $0.0058 | $0.0047 |
| Nova-3 (Monolingual) | Deepgram | $0.0077 | $0.0077 | $0.0065 |
| Nova-3 Medical | Deepgram | $0.0077 | $0.0077 | $0.0065 |
| Nova-3 (Multilingual) | Deepgram | $0.0092 | $0.0092 | $0.0078 |
| Scribe v2 Realtime | ElevenLabs | $0.0105 | $0.0105 | $0.0105 |

## Text-to-Speech (TTS)

| Model | Creator | Build (per 1M chars) | Ship (per 1M chars) | Scale (per 1M chars) |
|-------|---------|----------------------|---------------------|---------------------|
| Sonic | Cartesia | $50 | $50 | $37.50 |
| Sonic 2 | Cartesia | $50 | $50 | $37.50 |
| Sonic 3 | Cartesia | $50 | $50 | $37.50 |
| Sonic 3 (2025-10-27) | Cartesia | $50 | $50 | $37.50 |
| Sonic 3 (2026-01-12) | Cartesia | $50 | $50 | $37.50 |
| Sonic Turbo | Cartesia | $50 | $50 | $37.50 |
| Aura-2 | Deepgram | $30 | $30 | $27 |
| Eleven Flash v2 | ElevenLabs | $150 | $150 | $60 |
| Eleven Flash v2.5 | ElevenLabs | $150 | $150 | $60 |
| Eleven Multilingual v2 | ElevenLabs | $300 | $300 | $120 |
| Eleven Turbo v2 | ElevenLabs | $150 | $150 | $60 |
| Eleven Turbo v2.5 | ElevenLabs | $150 | $150 | $60 |
| Inworld TTS 1 | Inworld | $5 | $5 | $5 |
| Inworld TTS 1 Max | Inworld | $10 | $10 | $10 |
| Inworld TTS 1.5 Max | Inworld | $10 | $10 | $10 |
| Inworld TTS 1.5 Mini | Inworld | $5 | $5 | $5 |
| Arcana | Rime | $40 | $40 | $30 |
| Mist | Rime | $30 | $30 | $20 |
| Mist v2 | Rime | $30 | $30 | $20 |
| Mist v3 | Rime | $30 | $30 | $20 |
| Text to Speech | xAI | $4.20 | $4.20 | $4.20 |

## Large Language Models (LLM)

| Model | Creator | Metric | Build (per 1M tokens) | Ship (per 1M tokens) | Scale (per 1M tokens) |
|-------|---------|--------|----------------------|---------------------|---------------------|
| DeepSeek-V3 | DeepSeek | Input | $0.77 | $0.77 | $0.77 |
| DeepSeek-V3 | DeepSeek | Output | $0.77 | $0.77 | $0.77 |
| Gemini 2.5 Flash | Google | Cached input | $0.03 | $0.03 | $0.03 |
| Gemini 2.5 Flash | Google | Input | $0.30 | $0.30 | $0.30 |
| Gemini 2.5 Flash | Google | Output | $2.50 | $2.50 | $2.50 |
| Gemini 2.5 Flash-Lite | Google | Cached input | $0.01 | $0.01 | $0.01 |
| Gemini 2.5 Flash-Lite | Google | Input | $0.10 | $0.10 | $0.10 |
| Gemini 2.5 Flash-Lite | Google | Output | $0.40 | $0.40 | $0.40 |
| Gemini 2.5 Pro | Google | Cached input | $0.25 | $0.25 | $0.25 |
| Gemini 2.5 Pro | Google | Input | $2.50 | $2.50 | $2.50 |
| Gemini 2.5 Pro | Google | Output | $15.00 | $15.00 | $15.00 |
| Gemini 3 Flash | Google | Cached input | $0.05 | $0.05 | $0.05 |
| Gemini 3 Flash | Google | Input | $0.50 | $0.50 | $0.50 |
| Gemini 3 Flash | Google | Output | $3.00 | $3.00 | $3.00 |
| Gemini 3.1 Flash Lite | Google | Cached input | $0.025 | $0.025 | $0.025 |
| Gemini 3.1 Flash Lite | Google | Input | $0.25 | $0.25 | $0.25 |
| Gemini 3.1 Flash Lite | Google | Output | $1.50 | $1.50 | $1.50 |
| Gemini 3.1 Pro | Google | Cached input | $0.40 | $0.40 | $0.40 |
| Gemini 3.1 Pro | Google | Input | $4.00 | $4.00 | $4.00 |
| Gemini 3.1 Pro | Google | Output | $18.00 | $18.00 | $18.00 |
| Kimi K2.5 | Moonshot AI | Input | $0.60 | $0.60 | $0.60 |
| Kimi K2.5 | Moonshot AI | Output | $3.00 | $3.00 | $3.00 |
| GPT-4.1 | OpenAI | Cached input | $0.50 | $0.50 | $0.50 |
| GPT-4.1 | OpenAI | Input | $2.00 | $2.00 | $2.00 |
| GPT-4.1 | OpenAI | Output | $8.00 | $8.00 | $8.00 |
| GPT-4.1 mini | OpenAI | Cached input | $0.10 | $0.10 | $0.10 |
| GPT-4.1 mini | OpenAI | Input | $0.40 | $0.40 | $0.40 |
| GPT-4.1 mini | OpenAI | Output | $1.60 | $1.60 | $1.60 |
| GPT-4.1 nano | OpenAI | Cached input | $0.03 | $0.03 | $0.03 |
| GPT-4.1 nano | OpenAI | Input | $0.10 | $0.10 | $0.10 |
| GPT-4.1 nano | OpenAI | Output | $0.40 | $0.40 | $0.40 |
| GPT-4o | OpenAI | Cached input | $1.25 | $1.25 | $1.25 |
| GPT-4o | OpenAI | Input | $2.50 | $2.50 | $2.50 |
| GPT-4o | OpenAI | Output | $10.00 | $10.00 | $10.00 |
| GPT-4o mini | OpenAI | Cached input | $0.075 | $0.075 | $0.075 |
| GPT-4o mini | OpenAI | Input | $0.15 | $0.15 | $0.15 |
| GPT-4o mini | OpenAI | Output | $0.60 | $0.60 | $0.60 |
| GPT-5 | OpenAI | Cached input | $0.13 | $0.13 | $0.13 |
| GPT-5 | OpenAI | Input | $1.25 | $1.25 | $1.25 |
| GPT-5 | OpenAI | Output | $10.00 | $10.00 | $10.00 |
| GPT-5 mini | OpenAI | Cached input | $0.03 | $0.03 | $0.03 |
| GPT-5 mini | OpenAI | Input | $0.25 | $0.25 | $0.25 |
| GPT-5 mini | OpenAI | Output | $2.00 | $2.00 | $2.00 |
| GPT-5 nano | OpenAI | Cached input | $0.01 | $0.01 | $0.01 |
| GPT-5 nano | OpenAI | Input | $0.05 | $0.05 | $0.05 |
| GPT-5 nano | OpenAI | Output | $0.40 | $0.40 | $0.40 |
| GPT-5.1 | OpenAI | Cached input | $0.13 | $0.13 | $0.13 |
| GPT-5.1 | OpenAI | Input | $1.25 | $1.25 | $1.25 |
| GPT-5.1 | OpenAI | Output | $10.00 | $10.00 | $10.00 |
| GPT-5.1 Chat | OpenAI | Cached input | $0.13 | $0.13 | $0.13 |
| GPT-5.1 Chat | OpenAI | Input | $1.25 | $1.25 | $1.25 |
| GPT-5.1 Chat | OpenAI | Output | $10.00 | $10.00 | $10.00 |
| GPT-5.2 | OpenAI | Cached input | $0.18 | $0.18 | $0.18 |
| GPT-5.2 | OpenAI | Input | $1.75 | $1.75 | $1.75 |
| GPT-5.2 | OpenAI | Output | $14.00 | $14.00 | $14.00 |
| GPT-5.2 Chat | OpenAI | Cached input | $0.18 | $0.18 | $0.18 |
| GPT-5.2 Chat | OpenAI | Input | $1.75 | $1.75 | $1.75 |
| GPT-5.2 Chat | OpenAI | Output | $14.00 | $14.00 | $14.00 |
| GPT-5.3 Chat | OpenAI | Cached input | $0.175 | $0.175 | $0.175 |
| GPT-5.3 Chat | OpenAI | Input | $1.75 | $1.75 | $1.75 |
| GPT-5.3 Chat | OpenAI | Output | $14.00 | $14.00 | $14.00 |
| GPT-5.4 | OpenAI | Cached input | $0.50 | $0.50 | $0.50 |
| GPT-5.4 | OpenAI | Input | $5.00 | $5.00 | $5.00 |
| GPT-5.4 | OpenAI | Output | $22.50 | $22.50 | $22.50 |
| GPT-5.4 mini | OpenAI | Cached input | $0.075 | $0.075 | $0.075 |
| GPT-5.4 mini | OpenAI | Input | $0.75 | $0.75 | $0.75 |
| GPT-5.4 mini | OpenAI | Output | $4.50 | $4.50 | $4.50 |
| GPT-5.4 nano | OpenAI | Cached input | $0.02 | $0.02 | $0.02 |
| GPT-5.4 nano | OpenAI | Input | $0.20 | $0.20 | $0.20 |
| GPT-5.4 nano | OpenAI | Output | $1.25 | $1.25 | $1.25 |
| GPT OSS 120B | OpenAI | Input | $0.10 | $0.10 | $0.10 |
| GPT OSS 120B | OpenAI | Output | $0.50 | $0.50 | $0.50 |
| Qwen3 235B-A22B Instruct | Qwen | Input | $0.22 | $0.22 | $0.22 |
| Qwen3 235B-A22B Instruct | Qwen | Output | $0.80 | $0.80 | $0.80 |


# LiveKit Cloud Pricing Calculator Assumptions

## Default assumptions

- **LLM tokens per minute:** 3000 input, 175 output
- **TTS characters per minute:** 600

## Calculation rules

- **Connection type:** Either phone or web/mobile — only one applies at a time.
  - Phone: add telephony rate (US local, US toll-free, or third-party SIP). No WebRTC rate.
  - Web/mobile: add WebRTC connection rate. No telephony rate.
- **Realtime LLMs** (e.g. OpenAI GPT Realtime): STT and TTS are bundled into the realtime model rate, so their individual costs are $0.
- **External models** ("Other"): LLM cost is $0 through LiveKit — Billed by model provider directly.
- **Observability** is optional. When disabled, its cost is $0/min.
- **Third-party SIP vendor charges:** Third party SIP providers such as Twilio or Telnyx bill separately; ~$0.008/min is a good cost estimate.

### Total cost formula

`agent_session + (phone ? telephony : webrtc) + llm + (realtime_llm ? 0 : stt) + (realtime_llm ? 0 : tts) + (observability_enabled ? observability : 0)`

## How to estimate per-minute agent cost

Use these formulas with model prices from the inference pricing tables included above.

### Per-component formulas

- **LLM cost/min** = (input_tokens_per_min × price_per_1M_input_tokens / 1,000,000) + (output_tokens_per_min × price_per_1M_output_tokens / 1,000,000)
- **TTS cost/min** = characters_per_min × price_per_1M_characters / 1,000,000
- **STT cost/min** = per-minute rate from model data (direct)
- **Realtime LLM cost/min** = per-minute rate from realtime models table below (direct)

### Worked example (Ship plan, Phone-based voice agent)

Say you pick GPT-4o ($2.5/1M input, $10/1M output), Nova-2 ($0.0058/min STT), and Eleven Multilingual v2 ($300/1M chars TTS):

- LLM: (3000 × $2.5 / 1M) + (175 × $10 / 1M) = **$0.0092/min**
- STT: **$0.0058/min** (direct per-minute rate)
- TTS: 600 × $300 / 1M = **$0.1800/min**
- Agent session: **$0.0100/min**
- US local telephony: **$0.0100/min**
- Total: **~$0.2151/min**

## Fixed per-minute rates

| Service | Rate | Notes |
|---------|------|-------|
| Agent session | $0.01/min | Per-minute cost for an agent session deployed on LiveKit Cloud. |
| Connection and data transfer | $0.001/min | Estimate combining a connection rate of $0.0005/min and a data transfer rate of $0.12/GB. |
| US local inbound | $0.01/min |  |
| US toll-free inbound | $0.02/min |  |
| Third party SIP | $0.004/min | Connection fee to bring your own SIP provider such as Twilio or Telnyx. |
| Enabled | $0.01/min | Includes audio recording and assumes 100 entries per minute across transcripts, trace spans, and logs. |

## Realtime API models (manually maintained)

| Model | Rate | Assumptions |
|-------|------|-------------|
| OpenAI GPT Realtime | $0.0676/min | Assumes 3,200 input and 720 output tokens per minute (assumes 80% were cached tokens) |
| OpenAI GPT Realtime mini | $0.0216/min | Assumes 3,200 input and 720 output tokens per minute (assumes 80% were cached tokens) |
| Gemini Live 2.5 Flash Native Audio | $0.0144/min | Assumes 960 audio input and 960 audio output tokens per minute |
| Gemini Live 2.5 Flash | $0.0144/min | Assumes 960 audio input and 960 audio output tokens per minute |