← TPUs, AI chips & CPU endpoints
Compare 2 tpus, ai chips & cpu endpoints APIs
| HF Endpoints AWS Inferentia2 Hugging Face Inference Endpoints | HF Endpoints CPU (4 vCPU) Hugging Face Inference Endpoints | |
|---|---|---|
| $ / accel-hr | $0.75 Verified Oct 6, 2026 | $0.134 Verified Oct 6, 2026 |
| Quality | – | – |
| Speed | – | – |
| Accelerator type | inferentia | cpu |
| Memory | — | 8 GB |
| Frameworks | pytorch | onnx, pytorch |
| Supports training | No | No |
| Per-minute billing | Yes | Yes |