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#
Merge the model into Continue's config.yaml and enter your endpoint, API key and exact model ID before saving:
name: Managed inference
version: 1.0.0
schema: v1
models:
- name: Qwen3 32B
provider: openai
model: Qwen/Qwen3-32B
apiBase: https://weightsapi.com/v1
apiKey: WEIGHTSAPI_API_KEY
roles:
- chat
- edit
useResponsesApi: false
The exact field is apiBase, not baseURL. provider: openai is documented for compatible providers. Keep ordinary Chat/Edit as the basic recipe; agent mode additionally depends on native tool support. The default Qwen path already uses Chat Completions; explicit useResponsesApi: false makes the intended API surface clear.
Sources: OpenAI-compatible provider configuration, config.yaml reference.
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.