Paid requests#
There is no fixed requests-per-minute product limit by default. Admission is still subject to balance, key caps, model availability and physical capacity. A dedicated endpoint reserves the machine; shared capacity can queue.
Account-funded playground#
Sign in and confirm a top-up of at least USD 100 before AI use. Each later top-up has the same minimum; after qualification, a smaller remaining balance stays usable when it covers the request. Key permissions, spending caps and model availability still apply. Pending payments do not unlock access. Check service status before sending requests.
Context windows#
Input plus generated tokens must fit the configured deployment context. Published model-native windows and service ceilings are shown separately.
Dedicated capacity#
Dedicated machines use a prepaid monthly price without per-token charges. Throughput remains bounded by the machine and workload. Hardware availability and provisioning require confirmation; the service period starts on activation.
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
}'