LiveKit Inference Pricing
View all available inference models in our documentation
Contact sales for preferred rates on high-volume usage.
STT
Speech-to-Text|Documentation
| Provider | Model | Price |
|---|---|---|
AssemblyAI | Universal-Streaming | $0.150 / hour |
Universal-Streaming-Multilingual | $0.150 / hour | |
Cartesia | Ink Whisper | $0.180 / hour |
Deepgram | Flux | $0.462 / hour |
Nova-3 (Monolingual) | $0.462 / hour | |
Nova-3 (Multilingual) | $0.552 / hour | |
Nova-3 Medical | $0.462 / hour | |
Nova-2 | $0.348 / hour | |
Nova-2 Medical | $0.348 / hour | |
Nova-2 Conversational AI | $0.348 / hour | |
Nova-2 Phonecall | $0.348 / hour | |
ElevenLabs | Scribe V2 Realtime | $0.480 / hour |
LLMs
Large Language Models|Documentation
| Model family | Model | Provider | Input tokens price | Output tokens price |
|---|---|---|---|---|
OpenAI | GPT-4o | Azure | $2.50 / 1M | $10.00 / 1M |
GPT-4o | OpenAI | $2.50 / 1M | $10.00 / 1M | |
GPT-4o mini | Azure | $0.15 / 1M | $0.60 / 1M | |
GPT-4o mini | OpenAI | $0.15 / 1M | $0.60 / 1M | |
GPT-4.1 | Azure | $2.00 / 1M | $8.00 / 1M | |
GPT-4.1 | OpenAI | $2.00 / 1M | $8.00 / 1M | |
GPT-4.1 mini | Azure | $0.40 / 1M | $1.60 / 1M | |
GPT-4.1 mini | OpenAI | $0.40 / 1M | $1.60 / 1M | |
GPT-4.1 nano | Azure | $0.10 / 1M | $0.40 / 1M | |
GPT-4.1 nano | OpenAI | $0.10 / 1M | $0.40 / 1M | |
GPT-5 | Azure | $1.25 / 1M | $10.00 / 1M | |
GPT-5 | OpenAI | $1.25 / 1M | $10.00 / 1M | |
GPT-5 mini | Azure | $0.25 / 1M | $2.00 / 1M | |
GPT-5 mini | OpenAI | $0.25 / 1M | $2.00 / 1M | |
GPT-5 nano | Azure | $0.05 / 1M | $0.40 / 1M | |
GPT-5 nano | OpenAI | $0.05 / 1M | $0.40 / 1M | |
GPT OSS 120B | Baseten | $0.10 / 1M | $0.50 / 1M | |
GPT OSS 120B | Groq | $0.15 / 1M | $0.60 / 1M | |
GPT OSS 120B | Cerebras | $0.35 / 1M | $0.75 / 1M | |
Gemini | Gemini 2.5 Pro | $2.50 / 1M | $15.00 / 1M | |
Gemini 2.5 Flash | $0.30 / 1M | $2.50 / 1M | ||
Gemini 2.5 Flash Lite | $0.10 / 1M | $0.40 / 1M | ||
Gemini 2.0 Flash | $0.10 / 1M | $0.40 / 1M | ||
Gemini 2.0 Flash Lite | $0.07 / 1M | $0.30 / 1M | ||
Qwen | Qwen3 235B A22B Instruct (Deprecated. Retires December 19, 2025) | Baseten | $0.22 / 1M | $0.80 / 1M |
Kimi | Kimi K2 Instruct | Baseten | $0.60 / 1M | $2.50 / 1M |
DeepSeek | DeepSeek V3.1 | Baseten | $0.77 / 1M | $0.77 / 1M |
DeepSeek V3.2 | Baseten | $0.30 / 1M | $0.45 / 1M |
TTS
Text-to-Speech|Documentation
| Provider | Model | Price |
|---|---|---|
Cartesia | Sonic 3 | $50 / 1M characters |
Sonic 2 | $50 / 1M characters | |
Sonic Turbo | $50 / 1M characters | |
Sonic | $50 / 1M characters | |
Deepgram | Aura-1 | $15 / 1M characters |
Aura-2 | $30 / 1M characters | |
ElevenLabs | Eleven Flash v2 | $150 / 1M characters |
Eleven Flash v2.5 | $150 / 1M characters | |
Eleven Turbo v2 | $150 / 1M characters | |
Eleven Turbo v2.5 | $150 / 1M characters | |
Eleven Multilingual v2 | $300 / 1M characters | |
Inworld | Inworld TTS 1 Max | $10/ 1M characters Free through 12/31 |
Inworld TTS 1 | $5/ 1M characters Free through 12/31 | |
Rime | Arcana V2 | $50 / 1M characters |
Mist V2 | $50 / 1M characters |
Powering billions of calls in production for:
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