AI Rate CardWhisper 3 Large vs Whisper Large v3 Turbo: API price and specs
| Field | Whisper 3 Large | Whisper Large v3 Turbo |
|---|---|---|
| Lowest input, per 1M | $0.01 | — |
| Median input, per 1M | $0.01 | — |
| Lowest output, per 1M | $0.01 | — |
| Median output, per 1M | $0.01 | — |
| Lowest unit price | $0.00045 / minute +125.2% | $0.0001998 / minute |
| Cost of 1M in + 200k out | $0.012 | — |
| Context | 448 | 448 |
| Max output | 1K | 448 +56.2% |
| Providers | 4 | 4 |
| Regions | CZ, US | CZ |
| Accepts | audio | audio |
| Returns | text, transcription | text, transcription |
| Type | Speech to text | Speech to text |
| Free option | no | no |
| Cheapest provider | nearai | — |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
Frequently asked questions
Which has the larger context, Whisper 3 Large or Whisper Large v3 Turbo?
Whisper 3 Large: 448 tokens; Whisper Large v3 Turbo: 448 tokens.
Where can I use both Whisper 3 Large and Whisper Large v3 Turbo?
deepinfra, kosmik, ovhcloud