Open Whisper checkpoint for robust multilingual transcription and captioning
Whisper 3 Large by openai is offered by 7 providers on this page. Public prices are shown for 4 of them. Its reference price is $0.016 per 1M input tokens and $0 per 1M output tokens. The lowest paid channel is Scaleway at $0.003 / $0 per 1M, about 7.0× below the reference price. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 448 tokens, with an output limit of 4,096 tokens. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2023-09.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | First-party | Free | — | — | 0 | 4,096 | ||
| Scaleway | Cloud | $0.003 | $0 | — | — | 0 | 8,192 | |
| evroc | Cloud | $0.0023 | $0.0023 | — | — | 448 | 4,096 | |
| NEAR AI Cloud | Gateway | $0.01 | $0 | — | — | 448 | 448 | |
| Privatemode AI | Gateway | $0.016 | $0 | — | — | 448 | 4,096 | |
| Groq | Cloud | — | — | — | — | 0 | 0 | hostTable.undisclosed |
| Vercel AI Gateway openai/whisper-1 | Cloud | — | — | — | — | 0 | 0 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.