The compute layer
for AI applications.

Run inference across a global network of GPUs through a single API.

Start free Book a demo

Built for teams that outgrew the hyperscaler bill.

The open network

The open network
for inference at scale.

User request18ms· Nearest healthy node

HealthyBusyDown

Open network

A global mesh of GPUs, all in one network.

Automatic failover

Traffic reroutes in milliseconds.

Instant load balancing

Requests spread across every available node.

Uptime SLA available

Committed uptime, latency, and throughput on dedicated capacity.

Deploy with one API call

OpenAI-compatible. No code changes.

client = OpenAI(
  base_url="https://inference.computedlayer.com/v1",
  api_key="sk-••••••••••••"
)

Two ways to ship. Both live in under two minutes.

Rent dedicated GPUs or call any model through our OpenAI-compatible API.

GPU compute

Rent a GPU in seconds

1
Select capacity
Pick a GPU type, VRAM, region, and hourly price from available cards across the network.
2
Boot a machine
Choose an image (Ubuntu 24.04), attach a persistent volume, and launch the runtime.
3
Own the loop
SSH in with full control, install your stack, then monitor and scale as you go.

Ready in ~47sDeploy now

Inference endpoint

Or just call a model

1
Select a model
Use a hosted open model — no node setup, no cold-start wrangling.
2
Point your SDK
Swap the base URL and keep your existing OpenAI-compatible client and tools.
3
Serve traffic
Send requests; routing, autoscaling, and failover are handled for you.

View docs →

>base_url="https://inference.computedlayer.com/v1"

Pricing

Pay by the hour.
Nothing else.

Dedicated NVIDIA GPUs with SSH access and a persistent volume. Deposit $5 to get $10 and start deploying.

Best value

RTX 4090

$0.29/hr

24 GB VRAM$0.29/hr

Deploy RTX 4090

RTX 5090

$0.39/hr

32 GB VRAM$0.39/hr

Deploy RTX 5090

A100

from $0.80/hr

40 GB VRAM$0.80/hr
80 GB VRAM$1.10/hr

Deploy A100

H100

$2.60/hr

80 GB VRAM$2.60/hr

Deploy H100

Up to 90% cheaper than AWS, Azure, and GCP.

API & SDK

Control Computed Layer
from your own stack.

OpenAI-compatible API. GPU-native. Developer and agent friendly.

OpenAI-compatible

Drop-in compatible with the OpenAI API.

Simple & powerful

Create clusters, scale on demand, and manage everything via API.

computedlayer ~ api

# Create a GPU cluster
$ curl -X POST https://api.computedlayer.com/v1/clusters \
  -H "Authorization: Bearer $COMPUTED_LAYER_API_KEY" \
  -d '{"gpu":"h100","image":"vllm/vllm-openai","count":1}'

# Response
{
  "status": "running",
  "cluster_id": "clu_01H7X8ZJ7P2Q9KJY4V8B3YN9T",
  "endpoint": "https://clu_01H7X8ZJ7P2Q9KJY4V8B3YN9T.api.computedlayer.com/v1",
  "created_at": "2024-05-20T14:32:18Z"
}

View full API docs →

Ready to build?

Get your API key and start deploying in minutes.

$export COMPUTED_LAYER_API_KEY=cl_••••••••••••••

Create account →

FAQ

Answers before you ask.

Start relaying compute
today.

An OpenAI-compatible endpoint and GPUs from $0.18/hr. No contract, no minimums — deposit $5 to get $10 and start deploying.

Get started →Book a demo

The compute layer for AI applications.

The open networkfor inference at scale.