LiveKit Inference Pricing
LiveKit Inference credits are billed by model type: LLM by tokens, STT by duration, TTS by characters, turn detection and interruption by request, and realtime models in each provider's own unit, shown per model. Discounted rates are available for most STT and TTS models on the Scale plan. Preferred rates for high-volume usage are available with an Enterprise contract. For more details on model concurrency, voices, and supported features, visit our documentation.
Build
$0/mo
Ship
$50/mo
Scale
$500/mo
Enterprise
Custom
$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
5
20
50
Request more via dashboard
Custom
Zero data retention
Prompts, audio, and model outputs aren't logged or stored in LiveKit or underlying model providers
—
20 custom voices
50 custom voices
Custom
Included, with limits
Free for agents hosted on LiveKit Cloud. Self-hosted agents get a development allowance, then fall back to local models.
$0.50 per 1,000 requests
Free for agents hosted on LiveKit Cloud. Self-hosted agents get a development allowance, then pay per request.
$0.50 per 1,000 requests
Free for agents hosted on LiveKit Cloud. Self-hosted agents get a development allowance, then pay per request.
Custom
Included, with limits
Free for agents hosted on LiveKit Cloud. Self-hosted agents get a development allowance, then fall back to local models.
$1.20 per 1,000 requests
Free for agents hosted on LiveKit Cloud. Self-hosted agents get a development allowance, then pay per request.
$1.20 per 1,000 requests
Free for agents hosted on LiveKit Cloud. Self-hosted agents get a development allowance, then pay per request.
Custom
LLM pricing
Large Language Models|Documentation
Price per million tokens ($) | |||||
|---|---|---|---|---|---|
| Model family | Model | Provider | Input | Cached input | Output |
DeepSeek | DeepSeek-V4 Pro | vercel | $1.740 | $0.150 | $3.480 |
DeepSeek-V4.1 Flash | Baseten | $0.300 | $0.030 | $1.200 | |
Gemini | Gemini 3 Flash | $0.500 | $0.050 | $3.000 | |
Gemini 3.1 Flash Lite | $0.250 | $0.025 | $1.500 | ||
Gemini 3.1 Pro | $4.000 | $0.400 | $18.000 | ||
Gemini 3.5 Flash | $1.500 | $0.150 | $9.000 | ||
Gemini 3.5 Flash Lite | $0.300 | $0.030 | $2.500 | ||
Gemini 3.8 Flash | $0.750 | $0.075 | $3.750 | ||
Gemini 4 Argon | $4.0002.000 | $0.2000.100 | $20.00010.000 | ||
Gemini 3.6 Flash | $1.500 | $0.150 | $7.500 | ||
Gemini 3.7 Flash | $0.750 | $0.075 | $3.750 | ||
Gemma | Gemma 4 31B | LiveKit | $0.400 | $0.200 | $1.200 |
Kimi | Kimi K2.6 | vercel | $0.950 | N/A | $4.000 |
OpenAI | ChatGPT Latest | Azure | $5.000 | $0.500 | $30.000 |
ChatGPT Latest | OpenAI | $5.000 | $0.500 | $30.000 | |
GPT-4.1 | Azure | $2.000 | $0.500 | $8.000 | |
GPT-4.1 | OpenAI | $2.000 | $0.500 | $8.000 | |
GPT-4.1 mini | Azure | $0.400 | $0.100 | $1.600 | |
GPT-4.1 mini | OpenAI | $0.400 | $0.100 | $1.600 | |
GPT-4.1 nano | Azure | $0.100 | $0.030 | $0.400 | |
GPT-4o | Azure | $2.500 | $1.250 | $10.000 | |
GPT-4o | OpenAI | $2.500 | $1.250 | $10.000 | |
GPT-4o mini | Azure | $0.150 | $0.075 | $0.600 | |
GPT-4o mini | OpenAI | $0.150 | $0.075 | $0.600 | |
GPT-5 | Azure | $1.250 | $0.130 | $10.000 | |
GPT-5 | OpenAI | $1.250 | $0.125 | $10.000 | |
GPT-5 mini | Azure | $0.250 | $0.030 | $2.000 | |
GPT-5 mini | OpenAI | $0.250 | $0.025 | $2.000 | |
GPT-5 nano | Azure | $0.050 | $0.010 | $0.400 | |
GPT-5 nano | OpenAI | $0.050 | $0.005 | $0.400 | |
GPT-5.2 | Azure | $1.750 | $0.180 | $14.000 | |
GPT-5.2 | OpenAI | $1.750 | $0.175 | $14.000 | |
GPT-5.4 | Azure | $5.000 | $0.500 | $22.500 | |
GPT-5.4 | OpenAI | $5.000 | $0.500 | $22.500 | |
GPT-5.4 mini | OpenAI | $0.750 | $0.075 | $4.500 | |
GPT-5.5 | Azure | $10.000 | $1.000 | $45.000 | |
GPT-5.5 | OpenAI | $10.000 | $1.000 | $45.000 | |
GPT-5.6 Luna | Azure | $0.200 | $0.020 | $1.200 | |
GPT-5.6 Luna | OpenAI | $0.200 | $0.020 | $1.200 | |
GPT-5.6 Sol | Azure | $4.000 | $0.400 | $20.000 | |
GPT-5.6 Sol | OpenAI | $4.000 | $0.400 | $20.000 | |
GPT-5.6 Terra | Azure | $2.000 | $0.200 | $12.000 | |
GPT-5.6 Terra | OpenAI | $2.000 | $0.200 | $12.000 | |
GPT-6 Luna | OpenAI | $0.100 | $0.010 | $0.500 | |
GPT-6 Sol | OpenAI | $2.000 | $0.200 | $10.000 | |
GPT OSS 120B | Baseten | $0.100 | N/A | $0.500 | |
GPT OSS 120B | Groq | $0.150 | $0.075 | $0.600 | |
GPT-5.1 | Azure | $1.250 | $0.130 | $10.000 | |
GPT-5.1 | OpenAI | $1.250 | $0.125 | $10.000 | |
GPT-5.4 nano | OpenAI | $0.200 | $0.020 | $1.250 | |
SpaceXAI | Grok 4.20 | SpaceXAI | $2.000 | N/A | $6.000 |
Grok 4.20 Reasoning | SpaceXAI | $2.000 | N/A | $6.000 | |
Grok 4.20 Multi-Agent | SpaceXAI | $2.000 | N/A | $6.000 | |
Grok 4.3 | SpaceXAI | $1.250 | $0.200 | $2.500 | |
Grok 4.5 | SpaceXAI | $2.000 | $0.500 | $6.000 | |
Grok 4.6 | SpaceXAI | $2.000 | $0.500 | $6.000 | |
Grok 4.7 | SpaceXAI | $2.000 | $0.500 | $6.000 | |
The above table scrolls horizontally on narrow screens
STT pricing
Speech-to-Text|Documentation
Price per minute ($) | |||
|---|---|---|---|
| Provider | Model | Build/Ship | Scale |
AssemblyAI | Universal-3.6 Pro Streaming | $0.0075 | $0.0075 |
Universal-3.5 Pro Streaming | $0.0075 | $0.0075 | |
Universal-Streaming | $0.0025 | $0.0025 | |
Universal-Streaming-Multilingual | $0.0025 | $0.0025 | |
Deepgram | Flux | $0.0065 | $0.0057 |
Flux (Multilingual) | $0.0078 | $0.0068 | |
Nova-3 (Monolingual) | $0.0048 | $0.0042 | |
Nova-3 (Multilingual) | $0.0058 | $0.0050 | |
Nova-3 Medical | $0.0077 | $0.0065 | |
Nova-3 Pharma | $0.0048 | $0.0042 | |
Nova-2 | $0.0058 | $0.0047 | |
Nova-2 Conversational AI | $0.0058 | $0.0047 | |
Nova-2 Medical | $0.0058 | $0.0047 | |
Nova-2 Phone Call | $0.0058 | $0.0047 | |
Cartesia | Ink 2 | $0.0090 | $0.0068 |
Ink Whisper | $0.0030 | $0.0023 | |
Gemini 3.5 Transcribe Live | $0.0095 | $0.0095 | |
Inworld | Inworld STT 1 | $0.0025 | $0.0017 |
OpenAI | GPT-Live Transcribe | $0.0170 | $0.0170 |
Speechmatics | Speechmatics Linden-1 | $0.0050 | $0.0050 |
SpaceXAI | Speech to Text | $0.0033 | $0.0033 |
Speech to Text 2 | $0.0033 | $0.0033 | |
The above table scrolls horizontally on narrow screens
Contact sales to discuss preferred STT rates and concurrency limits on an Enterprise contract.
TTS pricing
Text-to-Speech|Documentation
Price per million characters ($) | |||
|---|---|---|---|
| Provider | Model | Build/Ship | Scale |
Cartesia | Sonic 3 | $50.00 | $37.50 |
Sonic 3 (2026-01-12) | $50.00 | $37.50 | |
Sonic 3 Latest | $50.00 | $37.50 | |
Sonic 3.5 | $50.00 | $37.50 | |
Sonic 3.5 (2026-05-04) | $50.00 | $37.50 | |
Sonic 3.6 | $50.00 | $37.50 | |
Sonic 3.6 (2026-08-27) | $50.00 | $37.50 | |
Sonic Latest | $50.00 | $37.50 | |
Sonic Preview | $50.00 | $37.50 | |
Deepgram | Aura-2 | $30.00 | $27.00 |
Flux TTS | $45.00 | $40.50 | |
Fish Audio | Drama 3 | $50.0010.00 | $50.0010.00 |
S2 Pro | $15.00 | $15.00 | |
S2.1 Pro | $15.00 | $15.00 | |
Gemini 3.8 Flash-Lite TTS | $16.00 | $16.00 | |
Gemini 3.8 Flash TTS | $24.00 | $24.00 | |
Gradium | Gradium TTS | $48.00 | $36.00 |
Gradium TTS Beta | $48.00 | $36.00 | |
Inworld | Realtime TTS 1.5 Max | $35.00 | $20.00 |
Realtime TTS 1.5 Mini | $15.00 | $8.00 | |
Realtime TTS 2.0 | $25.00 | $15.00 | |
Realtime TTS 2.0 Flash | $15.00 | $9.00 | |
Rime | Coda | $50.00 | $50.00 |
Mist v3 | $30.00 | $20.00 | |
SpaceXAI | Text to Speech | $15.00 | $15.00 |
The above table scrolls horizontally on narrow screens
Contact sales to discuss preferred TTS rates and concurrency limits on an Enterprise contract.
Realtime models
One model handles listening and speaking directly, with no separate STT, LLM or TTS stage. Billed in each provider's own unit, shown per model. Documentation
Token-billed
Price scales with usage — audio, text, and image tokens are each billed separately, the same way LLM pricing works.
Price per million tokens ($) | $/min | |||||
|---|---|---|---|---|---|---|
| Provider | Model | Modality | Input | Cached | Output | Transcription |
Gemini 3.8 Live | Audio | 3.00 | N/A | 12.00 | N/A | |
| Text | 0.75 | N/A | 4.50 | |||
| Image | 1.00 | N/A | N/A | |||
Gemini 3.8 Live Extended Thinking | Audio | 3.00 | N/A | 12.00 | N/A | |
| Text | 0.75 | N/A | 4.50 | |||
| Image | 1.00 | N/A | N/A | |||
OpenAI | GPT Realtime 2.1 | Audio | 32.00 | 0.40 | 64.00 | 0.003 |
| Text | 4.00 | 0.40 | 24.00 | |||
| Image | 5.00 | 0.50 | N/A | |||
GPT Realtime 2.1 mini | Audio | 10.00 | 0.30 | 20.00 | 0.003 | |
| Text | 0.60 | 0.06 | 2.40 | |||
| Image | 0.80 | 0.08 | N/A | |||
The above table scrolls horizontally on narrow screens
Contact sales to discuss preferred realtime rates and concurrency limits on an Enterprise contract.
Powering billions of calls in production for:
Looking for preferred rates?
Contact sales to discuss preferred rates through our Enterprise plan.
No credit card required • 1,000 free agent session minutes monthly