Open models on your hardware, at cloud latency.

Bastion is an inference runtime that serves open LLMs inside your own datacenter or VPC. Your data never leaves your network — and you stop paying per token to sit behind someone else's rate limits.

We benchmark Bastion on your model and your hardware. No data leaves your side.

Thanks — we'll reach out to set up a benchmark within a day.

bastion bench · llama-3.1-70b · 8×H100
$ bastion bench --model llama-3.1-70b --slo p95=300ms
 throughputp50 latency$ / 1M tokegress
Hosted API2,400 tok/s210 ms$2.80all prompts
Bastion (on-prem)5,900 tok/s90 ms$0.42none

Illustrative. Actual numbers come from a benchmark on your workload.

What Bastion does

deployRuns where your data already lives

A single container or Helm chart into your Kubernetes cluster or bare metal. Air-gapped installs are supported. No traffic to us, no model weights leaving your perimeter, no third-party API in the path.

Works with your existing GPUs — H100, A100, L40S, MI300X.

serveTuned for throughput, not demos

Continuous batching, paged attention, FP8 and INT4 quantization, and speculative decoding — with kernels tuned per GPU. The same weights that crawl on a naive server saturate your hardware here.

OpenAI-compatible endpoint, so your apps point at it without a rewrite.

governBuilt for teams that get audited

Per-token usage and cost metrics, autoscaling across your nodes, SSO, and audit logs. The people who need on-prem inference usually need to prove where the data went, too.

Every request stays inside your compliance boundary, by construction.

Who it's for

Teams running real inference volume under data-residency or sovereignty constraints — where sending prompts to a hosted API is either a compliance problem or a line-item that grows with every user. If you've already decided the models run on your side, Bastion is the runtime that makes them fast.

financial services healthcare & pharma defense & gov insurance telecom legal

Benchmark it on your workload

Tell us the model and the hardware you're targeting. We'll run Bastion against your current setup and send back throughput, latency, and cost — measured, not promised.

Thanks — we'll reach out to set up a benchmark within a day.