LiveKit Inference
Hosted access to speech-to-text, LLM and text-to-speech models and turn-handling models through one API key, with zero data retention by default.
Find alternatives to LiveKit Inference
What it does
- Model inference
Sources
- Pricing
-
Price evidence read 2026-11-16: "LiveKit Inference credits Call popular models with LiveKit's inference service $2.50 in credits" "LLM by tokens, STT by duration, TTS by characters".
- Description
-
Official documentation · 16 Nov 2026
Page text fetched 2026-11-16 (curl, full text read); page quote: "With LiveKit Inference, you can iterate quickly and swap models with a single line of code, with zero data retention by default.".
- What it does
-
Official documentation · 16 Nov 2026
Page text fetched 2026-11-16 (curl, full text read); page quote: "With LiveKit Inference, you can iterate quickly and swap models with a single line of code, with zero data retention by default.".
- Sold within
-
Plans include monthly inference credits and then bill per model; the inference price table has its own page. Quote: "LiveKit Inference credits Call popular models with LiveKit's inference service".
- Name
-
Official documentation · 16 Nov 2026
Page text fetched 2026-11-16 (curl, full text read); page quote: "With LiveKit Inference, you can iterate quickly and swap models with a single line of code, with zero data retention by default.".
- URL
-
Official documentation · 16 Nov 2026
Page text fetched 2026-11-16 (curl, full text read); page quote: "With LiveKit Inference, you can iterate quickly and swap models with a single line of code, with zero data retention by default.".
- Interfaces
-
Official documentation · 16 Nov 2026
Page text fetched 2026-11-16 (curl); page quote: "Access LLM, STT, TTS, and turn handling models with a single API key".
Also from LiveKit
-
LiveKit Agent Platform Agent platform
LiveKit Agent Platform provides SDKs, hosted agent deployment, model inference, telephony integration, and observability for realtime AI agents.
-
Agent Builder Application
Browser-based builder where a voice agent is configured with a prompt, model and actions, previewed live and deployed to LiveKit Cloud as executable Python.
-
Agent Observability Application
Turn-by-turn traces, logs, metrics and synchronised audio playback for each conversation a voice agent has on LiveKit Cloud.
-
Agent Simulations Application
Runs a voice agent against LLM-driven simulated users in text and audio, evaluates the conversations and turns production failures into test cases.
Something wrong here? Send a correction — quote this product id: livekit-inference.