Seligo API documentation

One control plane for every model you use — from the big labs to your own private GPUs. This is the customer-facing reference for building against the Seligo API and for spinning up a private GPU through that same API.

Base URL

All API calls go to https://api.seligo.cloud/v1. The router is OpenAI-compatible, so any client that speaks the OpenAI API can point at it.

export SELIGO_BASE="https://api.seligo.cloud/v1"

How it fits together

Org + user setup happens in the console at console.seligo.cloud — create an org, add members, top up your balance, and generate an API key.
Keys (rk-…) authenticate every API call. Each key is scoped to an org & user, so billing and usage follow the right principal.
Public models come from the catalogue — OpenAI-compatible chat/completions with built-in metering and pricing in EUR.
Private GPUs are on-demand dedicated LLM hosts you can start, infer on, and stop through the API — see Private GPU.

Quick starts

What	Where to look
Create your org, key & balance	Getting started
Call a public model	API reference — chat
List available models	API reference — models
Start / infer on / stop a private GPU	Private GPU

Try it now: once you have a key, this is all you need for a first call. Replace rk-… and pick any catalogue model from GET /v1/models.

curl -s "$SELIGO_BASE/chat/completions" \
  -H "authorization: Bearer rk-…" \
  -H "content-type: application/json" \
  -d '{"model":"scaleway/Meta-Llama-3-1-8B-Instruct",
       "messages":[{"role":"user","content":"Say hello"}]}'