AI infrastructure your customers can say yes to

Run open models securely on sovereign compute at a fixed monthly price, all behind one OpenAI-compatible API. Built for teams in regulated industries handling sensitive data.

UK GDPR compliant
Zero data retention
E2E encryption available
Cyber Essentials certified

How It Works

One platform for running open models on hardware you trust.

Install a worker on your own GPUs, or use ours. Pull open-weight models onto it. Call them through one API.

your-gpu-box
curl -sSL get.pendra.ai/worker | sh
Detected GPU: NVIDIA L40S · 48 GB
Paste your worker key: MC4CAQAwBQYDK2VwBCIEI…
Worker connected to Pendra
01

Install a worker

One command on Linux, installers for macOS and Windows, or a Docker image. The worker connects out to Pendra. Nothing inbound, nothing exposed. Or skip this step and use our managed UK GPUs, with serving, scaling and failover handled.

Linux macOS Windows Docker
Install a worker
your-gpu-box · worker online
qwen3.6:27b Serving
llama3.3:70b Installing… ✓ Installed
gemma4:26b deepseek-v4-flash swap any time
02

Load your models

Pull open-weight models onto your hardware from the console or CLI: Qwen, Llama, DeepSeek, Gemma, gpt-oss and more. Install, swap and pin them without touching the box again.

Chat Embeddings Vision Audio
Browse the models
app.py
client.chat.completions.create(
  model="qwen3.6:27b",
  stream=True,
)
→ Tokens stream straight from your GPU…
Zero retention · E2E encryption available
03

Call one API

OpenAI- and Anthropic-compatible endpoints with Python and Node.js SDKs. Your existing code just works. Zero retention by architecture, and end-to-end encryption seals prompts to your worker.

OpenAI-compatible Anthropic-compatible Streaming
Read the quickstart

Deployment

Run on our GPUs. Or bring your own. Or both.

Pendra is a hybrid platform. Use our managed infrastructure, deploy workers on your own hardware, or mix the two. We orchestrate everything through a single API.

Pendra-Managed Workers
We run the hardware. You call the API.
Your App
Pendra · UK
Pendra API
Pendra-managed workers
Worker A
4× A100 80GB
llama3.3:70b
Worker B
2× H100 80GB
gpt-oss:120b
Fully managed · zero retention · UK region
Self-Hosted Workers
Your GPUs. Our orchestration layer.
Your App
Pendra · UK
Pendra API
Self-hosted workers
Worker A
8× L40S 48GB
qwen3.6:35b
Worker B
4× A100 80GB
deepseek-v4-flash
Inference runs in your environment

Developer Experience

Five minutes to first inference.

Drop-in compatible with the OpenAI SDK. Native clients for Python and Node.js. Swap your base URL and your existing code works.

SDKs: Python Node.js + OpenAI compatible
quickstart.py
from pendra import Pendra

client = Pendra(api_key="pdr_sk_...")

# Same interface. Sovereign infrastructure.
response = client.chat.completions.create(
  model="gpt-oss:120b",
  messages=[{
    "role": "user",
    "content": "Summarise this discharge note."
  }]
)

print(response.choices[0].message.content)
Connected · api.pendra.ai · TLS 1.3 · UK Region

Jurisdiction

Your data stays in your jurisdiction. Not even legally reachable.

Sovereignty isn't a region setting — it's the architecture. Run on our UK compute, or on your own GPUs in your own country, under your own law. Either way, no foreign government, including the US, can reach your data.

UK hosted
or on your own hardware
Zero
data retained
US CLOUD Act
out of scope
E2E
encryption available

Use Cases

Your data processing shouldn't stop at the compliance boundary.

Regulated organisations sit on some of the most valuable unstructured data in the world: clinical notes, case files, citizen correspondence, claims documentation. Today, most of it stays locked because the infrastructure to process it privately doesn't exist.

Pendra is the platform for running open models on hardware you trust — ours or yours. Install a model, call it through one API, and keep every token inside your compliance boundary. Teams in healthcare, legal, government and finance build on it where privacy isn't optional.

console.pendra.ai · requests
Healthcare qwen3.6:27b

Clinical document processing

Summarise records, extract from discharge notes, triage correspondence, without data leaving your jurisdiction.

Legal llama3.3:70b

Privileged document review

LLM-assisted review across contracts, briefs and discovery sets on infrastructure that preserves privilege.

Public Sector gemma4:26b

Citizen data automation

Classification, redaction and response drafting for FOI requests, benefits processing and case management.

Financial Services deepseek-v4-flash

Compliant document intelligence

Process claims, extract KYC data and run agentic workflows under full regulatory control.

Processed in RAM · nothing stored · your jurisdiction

Where We're Going

Building the long-term compute layer for private AI.

Pendra isn't just an inference API. We're building the infrastructure stack that makes private, efficient AI processing the default, not the exception.

Now

Next

Future

Managed & hybrid inference

Open-weight models on our UK hardware or your own, delivered as a managed API with end-to-end encrypted private inference.

Advanced security controls

Automatic redaction, granular audit logging, deeper compliance tooling.

Purpose-built inference hardware

Dedicated silicon optimised per architecture. Faster, cheaper inference designed from the chip up.

Get in touch

Building AI products for regulated industries?

If you're building an AI product for healthcare, legal, public sector or finance, we're the inference layer behind it. Sovereign by architecture, compliance-ready, and proven on UK infrastructure, so you can ship without owning the regulatory surface yourself. Let's talk.