Skip to main content

Quickstart

Create an API key and make your first serverless inference call. You will need an FPT AI Factory account with credits — go to Billing to top up before you start.

Step 1: Browse the Model Catalog​

  1. In the left sidebar, click Serverless Inference.
  2. Click Models to see all available models.
  3. Each model card shows the model name, provider, context window, and per-token pricing.

Note the model name you want to use — you will pass it in the API request body.

See detailed guide: Browse the Model Catalog

Step 2: Create an API Key​

  1. Click API Keys in the Serverless Inference sidebar.
  2. Click + Create API Key.
  3. Enter a Name for the key (e.g. quickstart-test).
  4. Select the models this key is allowed to call (or keep Select all).
  5. Click Create, then copy the key — it is shown only once.

Create an API Key dialog

See detailed guide: Create an API Key

Step 3: Call the API​

Send a request to the serverless gateway. The gateway base URL is shown in the API Keys page and each model's detail card.

curl https://<serverless-gateway-domain>/v1/chat/completions \
  -H "Authorization: Bearer <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<model-name>",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 256
  }'

Replace <serverless-gateway-domain>, <your-api-key>, and <model-name> with your actual values.

See detailed guide: Call the Inference API

Step 4: Check your usage​

  1. Click Usage in the Serverless Inference sidebar.
  2. The dashboard shows month-to-date totals: requests, tokens in, tokens out, and estimated cost.
  3. The Tokens by model table breaks down usage per model; Usage by API Key shows per-key spend.

Serverless Inference — Usage tab

See detailed guide: Monitor Usage & Billing