$600k
“$600k of resources saved per year”
As published on baseten.co, September 2023. Checked by usedby on Oct 9, 2026.
What happened
Patreon uses Baseten to deploy and scale the Whisper transcription model, which transcribes audio and video content uploaded by creators and generates closed captions for its native video product. This lets the ML team avoid building and managing the underlying infrastructure themselves.
Summary written by usedby from the source page, in English. The figures are those of Baseten and Patreon, not ours.
- 440+ hours“440+ hours of dev time saved per year”
- 70%“70% savings in GPU cost”
In addition, he adds that Baseten is half the price of serving Whisper via OpenAI, while offering fine-grain control and security plus compliance guarantees.
Running our models on Baseten is more cost-effective than anything else in terms of vertical-specific solutions. It’s twice as cheap as the next cheapest solution. That plus their product improvement velocity and ticking the right compliance markers for us made working with Baseten the perfect partnership.
What the story claims, and what we checked
What we compared with the page.
- The figure: $600kCheckedPrinted word for word on the page, near the name of Patreon.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of Patreon.
- The publication dateCheckedRead from the page’s own metadata, never guessed.
- Patreon uses BasetenCheckedConfirmed line.
- The result itselfNot checkedWe quote it; we did not measure it.
More stories
Same company, same tool or same industry.
