# DeepInfra

Check the cited vendor page before you rent from DeepInfra.

Inference platform serving open and proprietary models via API priced per token or per unit, plus custom model deployments on dedicated A100, H100, H200, B200 and B300 GPUs billed by the minute.

## Details

- Address: Online, Global, United States
- Website: [deepinfra.com/](<https://deepinfra.com/>)
- GPU models: B300, B200, H200, H100, A100
- Lowest on-demand H100 rate: 290 US cents/GPU-h
- Lowest on-demand A100 rate: 149 US cents/GPU-h
- Billing: per minute
- Documentation: [deepinfra.com/docs](<https://deepinfra.com/docs>)
- Source note: Facts from the vendor's own website (https://deepinfra.com/pricing), fetched 2026-10-29.

## Questions

### Where is DeepInfra?

DeepInfra is at Online, Global, United States.

### How do I contact DeepInfra?

To contact DeepInfra, visit https://deepinfra.com/.

## Source

From [Vendor websites and documentation](https://deepinfra.com/pricing), license Facts compiled from public vendor pages. Source text and trademarks remain with their owners., checked 2026-10-29.

Last updated October 29, 2026.

## Links

- This GPU cloud provider on the [web page](<https://gpuclouds.fyi/us/global/online/deepinfra>)
- [Inference platforms in Online](<https://gpuclouds.fyi/us/global/online/category/inference-platforms.md>)
- [Serverless GPU in Online](<https://gpuclouds.fyi/us/global/online/category/serverless-gpu.md>)
- [More GPU cloud providers in Online](<https://gpuclouds.fyi/us/global/online.md>)