Whisper Large v3 vs Deepgram Nova-3
Whisper Large v3 is an open-weight speech-to-text model you can call on this endpoint; Deepgram Nova-3 is a closed model from Deepgram. Below: what each costs for three realistic workloads, the limits that apply, and when to choose which.
Deepgram figures are public list prices and documented limits, checked 2026-09-16 against the provider page. Inference APIs prices are read live from the price list.
- Cost: Whisper Large v3 is cheaper in all three workloads, by 74%.
- Limits: Deepgram: Concurrency limits by plan. Here: no per-minute or per-day caps.
Side by side
| Whisper Large v3 | Deepgram Nova-3 | |
|---|---|---|
| Served by | Inference APIs | Deepgram |
| Model author | OpenAI | Deepgram |
| Model id | openai/whisper-large-v3 | nova-3 |
| Price | $0.002 / audio minute | $0.0077 / audio minute |
| Capabilities | Speech to text, 100 languages, Word timestamps, Speaker diarization, SRT / VTT | Speech to text, Streaming, Diarization, Keyterms |
| Weights | Open | Closed |
| Status | Available | Available |
| Limits | No per-minute or per-day request or token caps; usage draws on a prepaid balance | Concurrency limits by plan. |
| Speed | 0.047× real time (19.5 s clip in 0.92 s) | not measured by us |
What three workloads cost
List prices applied to the same work. The cheaper side of each row is in bold.
| Workload | Whisper Large v3 | Deepgram Nova-3 | Difference |
|---|---|---|---|
| 1 hour of audio | $0.12 | $0.46 | 74% |
| 100 hours of audio | $12.00 | $46.20 | 74% |
| 1,000 hours of audio | $120 | $462 | 74% |
Whisper Large v3 is cheaper in all three workloads, by 74%.
When to choose which
- Cost is the deciding factor; it is cheaper in every workload above
- You want open weights: the same model can be moved to another host or self-hosted later
- Broad language coverage with automatic language detection
- Files up to 100 MB and SRT or VTT subtitles straight from the API
- Speaker labels with diarize=true, at the same price
- You only transcribe recorded files and want the lowest per-minute price
- You need real-time streaming transcription
- You need speaker diarization or keyterm prompting
Measured speed
Median of three runs on 2026-09-16: a 19.5-second mp3 clip, timed from upload to response. Expect ±30% with time of day. We did not measure Deepgram and do not quote other people's numbers; read "not measured" as unknown, not slow. Method and raw numbers: speed measurements.
FAQ
Which is cheaper, Whisper Large v3 or Deepgram Nova-3?
Whisper Large v3 is cheaper in all three workloads, by 74%. The table above uses list prices: Whisper Large v3 $0.002 / audio minute; Deepgram Nova-3 $0.0077 / audio minute.
What limits apply to Deepgram Nova-3?
Concurrency limits by plan. On Inference APIs there are no per-minute or per-day request or token caps; usage draws on a prepaid balance.
Spotted a price or limit that has changed? Tell us and we will re-check the provider page.