Your first request
Create a key, select an available model, send a request, then read its receipt.
Replace the placeholders with your deployment URL, your key and a model ID shown as available.
curl https://YOUR-INFERA-DOMAIN/v1/chat/completions \
-H "Authorization: Bearer $INFERA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "MODEL_ID_FROM_CATALOG", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 128}'1. Create an API key
Sign in, open API keys and create a key. Copy it immediately; Infera stores only a hash and cannot show it again. You can set an expiry, a spend limit and an allowed-model list.
2. Check your balance
Requests are refused when your prepaid Infera balance cannot cover the request's maximum cost. Lower max_tokens to reduce the reservation.
3. Pick an available model
Use the model ID shown as available on Infera's Models page or returned by GET /v1/models. Pending or unavailable models cannot receive requests.
4. Read the receipt
The response ID is the Infera request ID. GET /v1/requests/{id} or the Usage page shows the requested model, token counts, usage source and settled charge.