AI Rate CardGPT-Live-Transcribe vs GPT Realtime Whisper: API price and specs
| Field | GPT-Live-Transcribe | GPT Realtime Whisper |
|---|---|---|
| Lowest input, per 1M | — | $283.33 |
| Median input, per 1M | — | $283.33 |
| Lowest output, per 1M | — | — |
| Median output, per 1M | — | — |
| Lowest unit price | $0.017 / minute | $0.017 / minute |
| Cost of 1M in + 200k out | — | — |
| Context | — | 16K |
| Max output | — | 2K |
| Providers | 2 +33.3% | 3 |
| Regions | — | — |
| Accepts | audio, text | audio, text |
| Returns | text | text |
| Type | Speech to text | Speech to text |
| Free option | no | no |
| Cheapest provider | — | abacus |
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
Where can I use both GPT-Live-Transcribe and GPT Realtime Whisper?
openai, vercel