← TPUs, AI chips & CPU endpoints
Compare 4 tpus, ai chips & cpu endpoints APIs
| AWS Trainium2 (per chip) Amazon Web Services | HF Endpoints CPU (4 vCPU) Hugging Face Inference Endpoints | HF Endpoints AWS Inferentia2 Hugging Face Inference Endpoints | HF Endpoints Google TPU Hugging Face Inference Endpoints | |
|---|---|---|---|---|
| $ / accel-hr | $2.20 Unverified sample | $0.134 Verified Oct 6, 2026 | $0.75 Verified Oct 6, 2026 | $1.20 Verified Oct 6, 2026 |
| Quality | – | – | – | – |
| Speed | – | – | – | – |
| Accelerator type | trainium | cpu | inferentia | tpu |
| Memory | 96 GB | 8 GB | — | — |
| Frameworks | pytorch, jax | onnx, pytorch | pytorch | jax, pytorch |
| Supports training | Yes | No | No | No |
| Per-minute billing | Yes | Yes | Yes | Yes |