docs
models / Deepgram / Nova 3

Nova 3

audiodeepgram/nova-3ZDR supported

Transcribe audio using Deepgram’s speech-to-text model

$0.0052list priceper audio minute
pricing
unitlist → Elite price
per audio minute$0.0052
per audio minute (streaming)$0.0092

No Elite discount on this model right now: everyone pays the list price.

Everyone pays the list price. Reaching Elite (hold or stake 1,337 $XAVA, or hold 1,337,000 $XINF) unlocks the Elite price and a bigger buyback of your token. How it works

curl
curl https://www.zinf.ai/v1/media/generations \
  -H "Authorization: Bearer $XINF_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepgram/nova-3","input":{"text":"Hello from one key."}}'
limits
providerDeepgram
typeaudio
context window—
max output—
prompt storagenone
provider retentionnone ZDR supported
livesoon
requests 24h—
p50 latency—
uptime 7d—