OpenAI-compatible

Set up Continue

Continue keeps its providers in a config file. Add an entry with these keys.

The three values

Any ID from the models page.

Base URL: https://api.hubrium.com/v1
API key: Your Hubrium key
Model ID: deepseek-v3.1

json

{
  "provider": "openai",
  "apiBase": "https://api.hubrium.com/v1",
  "apiKey": "YOUR_HUBRIUM_API_KEY",
  "model": "deepseek-v3.1"
}

Call it in one request

Point your existing client at the Hubrium base URL and pass this model ID.

cURL

curl https://api.hubrium.com/v1/chat/completions \
  -H "Authorization: Bearer $HUBRIUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.1",
    "messages": [
      {"role": "user", "content": "Explain this code."}
    ],
    "stream": true
  }'

Hubrium

One integration, every model

Use the same API key and model IDs with OpenAI- or Anthropic-compatible request formats.

Get API key