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#
Current official Cursor help verifies Cursor Settings > Models, provider API key fields and Save, but lists supported providers rather than documenting arbitrary OpenAI-compatible base URLs or arbitrary Qwen IDs. It explicitly says BYOK is for chat and does not replace Tab completion; requests still pass through Cursor's servers.
Consequently an official-docs-only guide cannot honestly claim that https://weightsapi.com/v1 plus Qwen/Qwen3-32B works in Cursor's native model selector. Treat a native Cursor card as version-dependent / verify before use, not as a tested supported integration. Do not promise custom Tab/Composer support. The widely reported Override OpenAI Base URL and Add Custom Model flow needs a specific installed-version check beyond the current official documentation. No claim of successful native Qwen integration was established in this research.
Source: Cursor Bring your own API key.
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.