Deepgram models & pricing

Deepgram hosts 36 models covering 1 modalities. Nova/Aura speech-to-text and TTS — production-grade audio AI. Cheapest input starts at free tier; the most premium goes up to enterprise tier. Use Future AGI's Agent Command Center to route any Deepgram model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗
36

audio transcription 36

Model Input / 1M Output / 1M Context Caps
Base
Base Conversationalai
Base Finance
Base General
Base Meeting
Base Phonecall
Base Video
Base Voicemail
Enhanced
Enhanced Finance
Enhanced General
Enhanced Meeting
Enhanced Phonecall
Nova
Nova 2
Nova 2 Atc
Nova 2 Automotive
Nova 2 Conversationalai
Nova 2 Drivethru
Nova 2 Finance
Nova 2 General
Nova 2 Meeting
Nova 2 Phonecall
Nova 2 Video
Nova 2 Voicemail
Nova 3
Nova 3 General
Nova 3 Medical
Nova General
Nova Phonecall
Whisper
Whisper Base
Whisper Large
Whisper Medium
Whisper Small
Whisper Tiny

FAQ

How many Deepgram models are there?

36 Deepgram models are listed across 1 modality on this page. 0 have public per-token pricing.

How is Deepgram pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which Deepgram model is cheapest?

Several Deepgram models are free or have public-pricing pending. Browse the rows above and submit a source if you spot one we're missing.

Can I route to Deepgram via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Deepgram target, and call Deepgram models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any Deepgram model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.