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#
In Roo Code settings, set API Provider: OpenAI Compatible, Base URL: https://weightsapi.com/v1, API Key: WEIGHTSAPI_API_KEY, and Model: Qwen/Qwen3-32B. Use actual deployment limits for Context Window and Max Output Tokens.
Important integration condition: current official Roo Code docs say native OpenAI tool calling is mandatory and there is no XML fallback. Do not mark this integration supported unless the deployed Qwen endpoint has been tested with native tools and streamed tool arguments. Plain text chat success is insufficient.
Source: Roo Code official OpenAI-compatible documentation source.
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.