← TPUs, AI chips & CPU endpoints
Google (Gemini / Vertex)
Cloud TPU v6e (Trillium)
Per-chip on-demand price. Sample entry; the TPU pricing page text was not retrievable.
USD per accelerator- or instance-hour
$2.70
Unverified sample
#5 cheapest of 5 in TPUs, AI chips & CPU endpoints
Official pricing ↗Capabilities, explained
What this API can do, and what each capability means for your project.
Accelerator type
tpu
The kind of hardware you are renting.
Memory
32 GB
Memory per chip or instance. Sets the largest model you can load.
Frameworks
jax, pytorch, tensorflow, vllm
Software stacks that run on this hardware.
Supports training
Yes
Can be used to train models, not only to serve them.
Per-minute billing
No
You pay by the minute instead of rounding up to a full hour.
Price history
Only one price recorded so far. The chart appears once the price changes.