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.

Proof of change

LiveKit's pricing pages, as we captured them on two dates.

Capture only
Captured Aug 13, 2026 Captured Aug 14, 2026 · 1 days apart
inference
$3.75
Captured Aug 13, 2026
Captured Aug 14, 2026

Showing the whole page as captured — scroll either panel, or open it at full size.

Show 1 other page we compared
main
Captured Aug 13, 2026
Captured Aug 14, 2026

Showing the whole page as captured — scroll either panel, or open it at full size.

What these images do and don't show
  • These prices come from our capture alone — they were not confirmed against an independent second source.
  • 1 page had no counterpart in the earlier capture and is not shown.

Both images are our own captures, taken on the dates shown. The pixels are unmodified — nothing is retouched, and where a region is highlighted the marker is drawn over the image, not into it. Open either capture to see it at full resolution.

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

More LiveKit activity

All pricing activity