Deepgram Nova-3
Deepgram Nova-3 is worth evaluating for vision when its provider route and context window match the workload.
Use it for
- Teams evaluating vision
- Buyers comparing 1 tracked provider route
Do not use it for
- Strict JSON or tool-calling flows
- Family
- Deepgram Nova
- Released
- 2025-02-12
- Architecture
- neural
- Specialization
- transcription
- Openness
- Proprietary
- License
- ProprietaryCommercial use with conditions
- Training
- pretrained
Cheapest of 1 route · Deepgram API
About
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.
Deepgram Nova-3 is a proprietary model in the Deepgram Nova family. The structured metadata tracks multimodal input and audio. This page tracks provider routes through Deepgram API. No headline benchmark score is tracked for Deepgram Nova-3 yet.
Top use-case fit
Vision
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Deepgram API | - | - | ServerlessPartial |
Capabilities
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
nova-3nova-3-generalnova-3-medicalCheapest of 1 route · Deepgram API