Quickstart

Sign in, put credits on the organization, create a key, and send a chat completion. The OpenAI Python and JavaScript clients work if you set the base URL to Astorias.

Account and key

1. 1

   Sign in

   Open astorias.ai/sign-up. WorkOS creates the account on first login. If you have no organization yet, the app asks you to name one. That organization owns keys, usage, and credits.
2. 2

   Add credits

   Paid models need a credit balance. Admins top up at Billing. Packs start at $5. See Usage and billing.
3. 3

   Create an API key

   Organization admins create keys at APIs. Copy the ast_ key once and store it as ASTORIAS_API_KEY. Members cannot create keys. Details are in Authentication.

First request

Replace the braced placeholders — the {huggingface-model-id} model id and the {user-message} — with your own values. Model ids come from GET /v1/models or Model Garden. Tick Advanced to see every optional parameter; the capability fields only work on models that list them in the catalog.

# Minimal chat completion. Replace the braced placeholders.
# Every optional parameter is listed under Advanced.

curl \
  --request POST \
  --url "https://api.astorias.ai/v1/chat/completions" \
  --header "Authorization: Bearer $ASTORIAS_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "{huggingface-model-id}",
    "messages": [
      { "role": "user", "content": "{user-message}" }
    ]
  }'

What to read next

Chat completions is the full parameter reference, including streaming. Models explains how to read capabilities and prices from the catalog. Reasoning lists which reasoning efforts each model supports.