First Round

General Catalyst

Khosla Ventures

Kearny Jackson

Terrain

First Round

General Catalyst

Khosla Ventures

Kearny Jackson

Terrain

GPU server infrastructure
GPU server infrastructure
GPU server infrastructure

Scalable inference

Built for production inference.

One API for supported OSS and fine-tuned models, from first token to trillions per week.

0T+

Tokens served every week

0T+

Tokens served every week

0T+

Tokens served every week

20–0%

Typical inference cost reduction compared to other OSS providers

20–0%

Typical inference cost reduction compared to other OSS providers

20–0%

Typical inference cost reduction compared to other OSS providers