Before you connect#
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. Use your own API key without the Bearer prefix in key fields. The base URL already includes /v1. These configurations were checked against official documentation, not tested against a live GPU deployment.
Configuration#
Create an OpenAI credential with API Key equal to the service key and Base URL equal to https://weightsapi.com/v1. Leave Organization ID (optional) blank. Attach this credential to an OpenAI Chat Model node, choose/enter Model: Qwen/Qwen3-32B, and leave Use Responses API off. Attach the chat model to a Basic LLM Chain for an initial text-only test. AI Agent workflows require supported tool calling.
The current official credential source verifies Base URL exists in the credential, internally named url, and API Key is apiKey. Credential testing calls /models; authentication adds Authorization: Bearer ... itself.
Sources: OpenAI credential source, OpenAI Chat Model documentation, official documentation source fetched when the rendered page returned an unsupported content type.
Verify the connection#
Fetch the model list, then send one short message. A successful model list does not prove tools, vision or JSON schema support. Check the selected deployment’s capabilities before enabling them.