/
Obelisk Labs Pro Trial

Model Gateway

Attach an inference provider once and route every request — chat, image, speech — through a single project key.

Use Cases

Start from a working example and swap in your own provider keys.

Ship a support agent

Ground a chat assistant in your own docs with retrieval on every turn.

Render product art

Batch catalogue art from a prompt file with a diffusion endpoint.

Narrate long text

Turn release notes and articles into audio with a speech model.

All Providers

Adding a provider enables every service that provider supports.

Skiff Retrieval

Language models with live web lookup wired into the request path.

Emberflow

An inference host that specialises in diffusion and video models.

Cirrus Compute

Serverless GPU runtime built for AI and data teams.

Northlight

A cloud for running open-weight generative models at scale.

Browse Models