Inference APIs
Compare/Speech-to-text

Whisper Large v3 vs Whisper Large v3 Turbo

Two open-weight speech-to-text models on the same endpoint and API key, so switching between them is a one-word change. Below: what each costs for three realistic workloads, how they differ, and measured speed.

Inference APIs prices are read live from the price list.

Short answer
  • Cost: Both cost the same at list price.

Side by side

Whisper Large v3Whisper Large v3 Turbo
Served byInference APIsInference APIs
Model authorOpenAIOpenAI
Model idopenai/whisper-large-v3openai/whisper-large-v3-turbo
Price$0.001 / audio minute$0.001 / audio minute
CapabilitiesSpeech to text, 100 languages, Word timestamps, Speaker diarization, SRT / VTTSpeech to text, 100 languages, Word timestamps, Speaker diarization, SRT / VTT
WeightsOpenOpen
StatusAvailableAvailable
LimitsNo per-minute or per-day request or token caps; usage draws on a prepaid balanceNo per-minute or per-day request or token caps; usage draws on a prepaid balance
Speed0.047× real time (19.5 s clip in 0.92 s)—

What three workloads cost

List prices applied to the same work. The cheaper side of each row is in bold.

WorkloadWhisper Large v3Whisper Large v3 TurboDifference
1 hour of audio$0.06$0.06—
100 hours of audio$6.00$6.00—
1,000 hours of audio$60.00$60.00—

Both cost the same at list price.

When to choose which

Choose Whisper Large v3 if
  • 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 $0.002 a minute
  • Hard audio or rare languages, where full Whisper Large v3 is more accurate
Choose Whisper Large v3 Turbo if
  • Long files and batch jobs where speed matters more than the last bit of accuracy
  • Code written for Groq's whisper-large-v3-turbo id
  • An hour of audio in about 17 seconds for $0.06

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. Method and raw numbers: speed measurements.

Trying both

Same endpoint, same key. Change one string:

cURL
for MODEL in "openai/whisper-large-v3" "openai/whisper-large-v3-turbo"; do
  curl -s https://api.inferenceapis.com/v1/audio/transcriptions \
    -H "Authorization: Bearer $INFERENCE_API_KEY" \
    -F "model=$MODEL" -F "file=@meeting.mp3" | jq -r .text
done

FAQ

Which is cheaper, Whisper Large v3 or Whisper Large v3 Turbo?

Both cost the same at list price. The table above uses list prices: Whisper Large v3 $0.001 / audio minute; Whisper Large v3 Turbo $0.001 / audio minute.

How do I switch between them?

They are on the same endpoint and key. Change the model field from openai/whisper-large-v3 to openai/whisper-large-v3-turbo and nothing else.

Spotted a price or limit that has changed? Tell us and we will re-check the provider page.