1. Create your key#
Open the console, sign in, and create an API key. Copy it immediately; only its hash is stored. Set a spend cap and a model allowlist before using it in an application.
2. Confirm a qualifying top-up#
Each account top-up must be at least USD 100, including every recharge after the first. Only a confirmed qualifying top-up unlocks AI access; starting a payment or obtaining a quote does not. The minimum is an amount per top-up, not an ongoing minimum balance or a minimum API-key spending cap.
AI access requires sign-in, one confirmed top-up of at least USD 100, an authorized API key and enough available credit for the request. Each later top-up also has a USD 100 minimum; smaller remaining balances stay usable when they cover the request. Credit requires transaction verification. Check service status for model availability before sending traffic.
3. Send a request#
Base URL: https://weightsapi.com/v1. Use the exact model ID from a model page. The API key is a secret: keep it on your server, never in a public browser bundle.
4. Move to production#
Set a timeout, handle 429 and 503 with bounded exponential backoff, and cap max_tokens. Prompt and response content is not stored by this gateway. Token counts, billing records and key metadata are retained for accounting.
Service availability#
Check service status and model discovery before sending traffic. An unavailable deployment returns 503 service_unavailable. Creating an API key or funding order does not change model availability.
Request example
curl https://weightsapi.com/v1/chat/completions \
-H "Authorization: Bearer $WEIGHTSAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen3-32B",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": true
}'