
Own GPUs or API: where break-even lies
How many tokens per second must your GPU deliver to beat an API?
Slide contents
1. Own GPUs or API: where break-even lies
How many tokens per second must your GPU deliver to beat an API?
2. Utilization pays for own GPUs, not volume
Tokens per second a pair of H100s needs to match an API
3. From token price to a decision
The cluster series gave mechanisms; this deck adds money
4. API prices span fiftyfold
Dollars per million tokens: input, output and a 3:1 blend
5. An H100 hour costs $1.80 to $12.29
On-demand price per GPU, November 2026
6. Token price: hourly cost over work
Four factors, and only one appears on the GPU bill
7. Lower utilization raises the bar
Required tokens per second for an H100 pair at $3.95 an hour
8. Peak-sized capacity idles at night
The Orbit example and the serving lab's lesson
9. GPUs are only the first bill line
What adds to the GPU hour, and what stays with the API
10. Count the price of an accepted task
Tokens get twenty times cheaper; review does not
11. APIs have caching and batching too
Discounts that move the break-even point
12. Hundreds of fine-tunes, one base's price
One 80 GB A100 · Llama-7B · synthetic workload
13. Local boxes don't pay back in tokens
A $3,999 Ryzen AI Max+ 395, 128 GB, against API prices
14. Four questions before buying GPUs
Answer in order; the first yes decides
15. The calculation transfers a method, not numbers
Dated prices, host assumptions and what we did not measure
16. Measure first, buy second
Three takeaways and a one-day experiment