LLM Reference
Deepgram API

Using Deepgram Nova-3 on Deepgram API

Implementation guide · Deepgram Nova · Deepgram

Serverless

Deepgram API exposes Deepgram Nova-3 through model ID nova-3. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Deepgram API and generate an API key.
  2. 2
    Use the Deepgram API SDK or REST API to call nova-3 — see the documentation for request format.
  3. 3
    You'll be billed $0.005/min. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Deepgram API documentation for integration details.

Pricing on Deepgram API

TypeRate
Audio minute$0.005/min

Capabilities

MultimodalAudio

About Deepgram Nova-3

Nova-3 is Deepgram's current-generation speech-to-text model, released February 12, 2025. Achieves 6.84% median WER streaming and 5.26% batch — a ~54% improvement over competitors. Supports real-time multilingual transcription across 31 languages with self-serve keyterm prompting (up to 100 terms) and real-time redaction (up to 50 entity types). Also includes nova-3-medical specialization. Streaming: $0.0048/min (mono), $0.0058/min (multilingual); pre-recorded: $0.0077/min (mono). API ID: nova-3.

Full model details →

Model Specs

Released2025-02-12
ArchitectureAudio / Speech

More Models on Deepgram API

Deepgram Nova-2
All models on Deepgram API →

Provider

Deepgram API
Deepgram API

Deepgram

San Francisco, California, United States