zlacker

[parent] [thread] 3 comments
1. mdrzn+(OP)[view] [source] 2026-02-04 16:09:38
Is it 0.003 per minute of audio uploaded, or "compute minute"?

For example fal.ai has a Whisper API endpoint priced at "$0.00125 per compute second" which (at 10-25x realtime) is EXTREMELY cheaper than all the competitors.

replies(2): >>Oras+c5 >>tgrowa+ca2
◧
2. Oras+c5[view] [source] 2026-02-04 16:30:51
>>mdrzn+(OP)
I think the point is having it for real-time; this is for conversations rather than transcribing audio files.
replies(1): >>jamilt+fo
◧◩
3. jamilt+fo[view] [source] [discussion] 2026-02-04 17:52:51
>>Oras+c5
That quote was for the non-realtime model.
◧
4. tgrowa+ca2[view] [source] 2026-02-05 05:08:45
>>mdrzn+(OP)
Both AWS and Mistral prices above are per minute of input audio.
[go to top]