Provider pricing
Deepgram AI API pricing
Deepgram has 4 priced models in the public snapshot. For 1,000 input and 500 output tokens, Nova-2 has the lowest recorded request cost at $0.00075, with $0.3 input and $0.9 output per million tokens.
Best for
Voice agents, call-center analytics, and real-time transcription at scale.
Strengths
- Nova-3 ASR: top-tier WER with sub-300ms streaming latency
- Aura TTS: sub-200ms time-to-first-byte for voice agents
- Speaker diarization, language detection, and PII redaction built in
- On-prem deployment for HIPAA, SOC 2, and FedRAMP customers
Last updated: · Source: No official pricing URL recorded · Methodology
Frequently asked questions
How much does the Deepgram API cost?
Deepgram has 4 priced models in the public snapshot. For 1,000 input and 500 output tokens, Nova-2 has the lowest recorded request cost at $0.00075, with $0.3 input and $0.9 output per million tokens.
Which Deepgram model is cheapest?
Nova-2 is the lowest-cost recorded model for the 1,000-input/500-output example. Prices are $0.3 input and $0.9 output per million tokens; different workloads may change the ranking.
Does Deepgram have cached or batch prices?
Cached input: not separately recorded. Batch: not recorded in this dataset. Eligibility and cache-write charges depend on the provider; these discounts are not automatically stacked.
How often are provider prices verified?
The live pricing table synchronizes stored model records daily; public file snapshots update when the site is rebuilt. Synchronization is not independent provider verification. Snapshot updated 2026-10-31; only explicit per-model dates are verification records.