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#
Install the official OpenAI-API-compatible provider (langgenius/openai_api_compatible) if absent, then add the model under workspace model-provider settings. Fields for an LLM/chat model:
| Field | Value |
|---|---|
| Type | LLM |
| Model Name | Qwen/Qwen3-32B |
| API Key | WEIGHTSAPI_API_KEY |
| API Base URL | https://weightsapi.com/v1 |
| Completion mode | Chat |
| API Type | Chat Completions API (/chat/completions) |
| Model context size | Actual deployment context limit |
| Upper bound for max tokens | Actual deployment output limit |
| Vision Support | Not Support for this text-only model |
| Function Call Type | Not Support until native tools are verified |
The exact underlying credential names are api_key, endpoint_url, mode: chat, api_type: chat_completions, context_size, and max_tokens_to_sample. An optional model name for API endpoint (endpoint_model_name) can override the sent model name; leave blank when Model Name already matches. Use the base URL including /v1 for this LLM recipe; this plugin has different path handling for non-LLM types, so do not extend this recipe to embeddings without checking.
Sources: Official marketplace listing, official provider field schema.
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.