Ask
Launch

LiveKit Inference adds Google Gemini 3.7 Flash

LiveKit pricing

LiveKit Inference gained one new LLM SKU, Google Gemini 3.7 Flash, priced at $0.0029/min, while all LiveKit Cloud plan prices (Build free, Ship $50, Scale $500, Enterprise custom) held unchanged.

Before

LiveKit Inference LLM catalog's Gemini family ran Gemini 3 Flash through Gemini 3.6 Flash (no 3.7 entry).

After

Catalog adds Google Gemini 3.7 Flash at $0.0029/min ($0.750 input / $0.075 cached input / $3.750 output per million tokens), slotting between Gemini 3.6 Flash ($0.0058/min) and Gemini 3.5 Flash Lite ($0.0013/min). Build $0 / Ship $50 / Scale $500 / Enterprise custom are unchanged.

LiveKit added one new model to the LiveKit Inference catalog, the single-API-key LLM/STT/TTS service billed per minute of model time against each Cloud plan’s credit allotment. Google Gemini 3.7 Flash joins the Gemini family at $0.0029/min — $0.750 per million input tokens, $0.075 per million cached-input tokens, and $3.750 per million output tokens — landing between the existing Gemini 3.6 Flash ($0.0058/min) and Gemini 3.5 Flash Lite ($0.0013/min) entries on the published per-minute list.

No LiveKit Cloud plan price, allotment or overage rate moved: Build is still free, Ship starts at $50/mo, Scale at $500/mo, and Enterprise remains custom-quoted. This is the fourth LiveKit Inference catalog update since 2026-07-21, continuing the pattern of LiveKit restocking its model catalog on a roughly weekly-to-biweekly cadence without touching Cloud plan pricing.

From LiveKit's pricing timeline
Google Gemini 3.7 Flash added to LiveKit Inference

Plan structure holds (Build free / Ship $50 / Scale $500 / Enterprise custom). LiveKit Inference gains one new LLM SKU, Google Gemini 3.7 Flash, at $0.0029/min ($0.750 input / $0.075 cached input / $3.750 output per million tokens), slotting between Gemini 3.6 Flash and Gemini 3.5 Flash Lite on the published list.

About LiveKit
livekit.io ↗

LiveKit is an open-source real-time (WebRTC) stack plus a managed cloud (LiveKit Cloud) and an Agents framework for building voice and video AI agents; it powers OpenAI's ChatGPT voice mode.

Free tier
Yes
Commits
None
Transparency
public

LiveKit pricing history

  1. Aug 2026
    Two new STT SKUs join LiveKit Inference; xAI relabeled SpaceXAI
  2. Aug 2026
    Grok 4.1 Fast delisted; Rime Arcana swapped for Gradium TTS
  3. Aug 2026
    Google Gemini 3.7 Flash added to LiveKit Inference
  4. Aug 2026
    Deepgram Flux TTS added free; GPT-5.2/5.3 Chat removed from LiveKit Inference
  5. Aug 2026
    GPT-5.6 Luna and Terra repriced down in LiveKit Inference
Full LiveKit timeline

More LiveKit activity

All pricing activity