PRODUCT

Your model. Your GPU capacity. One endpoint.

Deploy a public, private, or fine-tuned model on dedicated GPU infrastructure. OneInfer handles provisioning, runtime configuration, scaling, and endpoint access from a single console.

Dedicated endpoint

Production deployment

Ready
1

Choose a model

Use a supported template or your private model.

2

Configure compute

Select GPU, provider, region, workers, and concurrency.

3

Deploy and call

Send requests through your stable OneInfer endpoint ID.

POST /v1/ula/chat/completions
BENEFITS

What is a dedicated endpoint?

It is an isolated model deployment backed by GPU resources configured for your workload. Unlike a shared Model API, its capacity and runtime settings belong to your deployment.

Dedicated capacity

Your requests are sent to the GPU workers assigned to your deployment, avoiding contention with shared API traffic.

Predictable configuration

Control GPU type and count, region, worker limits, concurrency, storage, and scaling behaviour for each endpoint.

Private model support

Deploy supported templates, Hugging Face models, or a custom model source without exposing the model through a public catalog.

FEATURES

From model selection to a callable API

OneInfer manages the deployment lifecycle while giving your team direct control over the settings that affect performance and cost.

Choose the model runtime

Start from a supported deployment template or configure a compatible model source for your use case.

Select GPU and region

Choose available compute by provider, GPU type, GPU count, and deployment region instead of managing cloud instances yourself.

Set workers and concurrency

Define minimum and maximum workers, scaling mode, and request concurrency to match your traffic pattern.

Provision from one console

Create, inspect, and delete deployments from the OneInfer console without maintaining a separate infrastructure workflow.

Call it through OneInfer

Use your OneInfer API key and endpoint ID to direct inference requests to the exact deployment you created.

Build an intelligent endpoint

Attach multiple dedicated or serverless endpoints behind one intelligent endpoint for routing, balancing, and failover policies.

Choose the right way to run inference

READ THE DOCS ›
MODEL APIS

Model APIs for instant access

Use shared, pay-as-you-go inference when you want to prototype quickly or your traffic is still variable.

EXPLORE MODEL APIS ›
DEDICATED

Dedicated endpoints for control

Use reserved deployment capacity when you need a private model, stable runtime configuration, or predictable production performance.

CREATE ENDPOINT ›
INTELLIGENT ROUTING

One endpoint for multiple backends

Group dedicated and serverless endpoints, then route requests according to latency, cost, load, or model policies.

EXPLORE ROUTING ›

Deploy your first dedicated endpoint