AI inference and GPUs services compared: free tiers and pricing
9 ai inference and gpus services, each with its free tier and lowest paid price as read from its pricing page.
| Service | Free tier | Lowest paid price | Checked |
|---|---|---|---|
| Baseten | Basic: $0/mo, pay as you go | — | 2026-10-23 |
| DeepInfra | — | From $0.06 per 1M input tokens and $0.18 per 1M output (smallest listed model) | 2026-10-23 |
| fal.ai | — | GPUs from $1.99/hr; H100 as low as $2.49/hr | 2026-10-23 |
| Fireworks AI | — | $0.008 per 1M tokens (embedding models up to 150M parameters) | 2026-10-25 |
| Hugging Face | Free Hub account | Pro $9/mo with $2 of inference credits | 2026-10-23 |
| Modal | Starter: $0/mo with $30/mo free credit, 3 seats | Team $250/mo plus compute ($100/mo credit) | 2026-10-23 |
| Replicate | Try for free | Hardware from $0.000025/sec (CPU); GPUs e.g. A100 $0.0014/sec ($5.04/hr), H100 $5.49/hr | 2026-10-23 |
| RunPod | — | GPU pods from $0.27/hr | 2026-10-23 |
| Together AI | — | From $0.15 per 1M input tokens (e.g. GLM-5.3-Flash, $0.50 output) | 2026-10-23 |

