Inference APIs
Compare/Speech-to-text

Voxtral Mini 3B vs Deepgram Nova-3

Voxtral Mini 3B 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.

Short answer
  • Cost: Voxtral Mini 3B is cheaper in all three workloads, by 83%.
  • Limits: Deepgram: Concurrency limits by plan. Here: no per-minute or per-day caps.

Side by side

Voxtral Mini 3BDeepgram Nova-3
Served byInference APIsDeepgram
Model authorMistral AIDeepgram
Model idmistralai/Voxtral-Mini-3B-2507nova-3
Price$0.0013 / audio minute$0.0077 / audio minute
CapabilitiesSpeech to text, 8 languages, Auto language, Lowest priceSpeech to text, Streaming, Diarization, Keyterms
WeightsOpenClosed
StatusAvailableAvailable
LimitsNo per-minute or per-day request or token caps; usage draws on a prepaid balanceConcurrency limits by plan.
Speed0.058× real time (23.1 s clip in 1.35 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.

WorkloadVoxtral Mini 3BDeepgram Nova-3Difference
1 hour of audio$0.08$0.4683%
100 hours of audio$7.80$46.2083%
1,000 hours of audio$78.00$46283%

Voxtral Mini 3B is cheaper in all three workloads, by 83%.

When to choose which

Choose Voxtral Mini 3B if
  • 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
  • Cheap, fast multilingual transcription in Voxtral's eight languages
  • Batch jobs where cost per minute matters most
  • You only transcribe recorded files and want the lowest per-minute price
Choose Deepgram Nova-3 if
  • You need real-time streaming transcription
  • You need speaker diarization or keyterm prompting

Measured speed

Median of three runs on 2026-09-16: a 23.1-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 We did not measure Deepgram and do not quote other people's numbers; read "not measured" as unknown, not slow.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, Voxtral Mini 3B or Deepgram Nova-3?

Voxtral Mini 3B is cheaper in all three workloads, by 83%. The table above uses list prices: Voxtral Mini 3B $0.0013 / 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.