# Deep Infra Inc.

> Deep Infra is a Palo Alto-based AI inference cloud that lets developers run hundreds of open-source machine learning models - large language models, image and video generation, speech, and embeddings - through a simple, OpenAI-compatible, pay-per-use API. The company owns and operates its own GPU fleet across multiple US data centers, processing trillions of tokens per week for companies that want production AI without managing infrastructure.

- **Founded:** 2022
- **Headquarters:** Palo Alto, California, United States
- **Founders:** Nikola Borisov (Co-Founder & CEO), Yessenzhar Kanapin (Co-Founder), Georgios Papoutsis (Co-Founder)
- **Team size:** ~25 employees
- **Products:** Serverless Inference API, Dedicated GPU Instances, Private Model Deployments, GPU Rental
- **Notable:** Raised $107M Series B (2026) to scale inference infrastructure., Scaled processing volume more than 8,000x since seed stage., Processes nearly five trillion tokens per week.

## Products & services

- **Serverless Inference API** — OpenAI-compatible API for 190+ open-source models spanning text generation, image and video generation, text-to-speech, speech recognition, and embeddings - billed per token or per inference second.
- **Dedicated GPU Instances** — Private endpoints on Nvidia A100, H100, H200, B200 and B300 GPUs with autoscaling for teams that need guaranteed capacity and isolation.
- **Private Model Deployments** — Host custom or fine-tuned models on Deep Infra's optimized inference stack with a private, no-logging endpoint.
- **GPU Rental** — Rent raw GPU capacity in Deep Infra's US-based data centers for custom workloads.

## Achievements

- Raised $107M Series B (2026) to scale inference infrastructure.
- Scaled processing volume more than 8,000x since seed stage.
- Processes nearly five trillion tokens per week.
- Serves 190+ open-source models through a single OpenAI-compatible API.
- Owns and operates GPU infrastructure across eight US data centers.
- SOC 2 and ISO 27001 certified.
- Took delivery of large shipments of Nvidia Blackwell GPUs.

## Latest updates

- **2026-05** — Closed a $107M Series B co-led by 500 Global and Georges Harik, with Nvidia, Samsung Next, Supermicro, Felicis and others participating.
- **2026** — Received large shipments of Nvidia Blackwell GPUs and expanded to eight US data centers, processing close to five trillion tokens per week.
- **2025-04** — Raised $18M Series A led by Felicis with advisor Georges Harik.

## Links

- Website: https://deepinfra.com
- LinkedIn: https://www.linkedin.com/company/deep-infra
- Twitter/X: https://twitter.com/DeepInfra
- GitHub: https://github.com/deepinfra

---

Profile page: https://yespress.io/deep-infra-inc
Published by YesPress — https://yespress.io
Last updated: 2026-06-09