NVIDIA Google TPU

TPU v5 Lite Pod (1 core)

TPU v5 Lite delivers accessible TPU cores for inference and small training runs with pay-as-you-go pricing.

Launch year
2024
Memory
32 GB HBM
Memory bandwidth
>900 GB/s
Peak FP16 / FP32
60 TFLOPS · 0 TFLOPS

Market snapshot

$0.51 /hr

Range $0.51 – $1.56

Catalog coverage

32 live offerings

Across 1 providers · 18 regions

  • TPU runtime integration
  • Low entry cost
  • Efficient inference
TPU v5 Lite Pod (1 core) render

Last refreshed Oct 20, 2025, 2:01 AM

Performance snapshot

Normalized versus NVIDIA A100 (=1.0). Values use public reference benchmarks for training and inference workloads.

  • TPU Throughput×0.50
  • Energy Efficiency×0.80
  • Latency×0.60

Provider availability

Price bands per provider pulled from the live catalog.

  • Google Cloud logoGoogle Cloud32 offers
    $0.51 – $1.56 /hr

Popular regions

  • us-west4-b2 offers
  • us-west4-a2 offers
  • us-east5-a2 offers
  • us-east5-c2 offers
  • us-east5-b2 offers
  • us-west1-c2 offers
  • us-central1-a2 offers
  • europe-west1-c2 offers

Weighted average price $1.04 /hr · median $1.20