Unverified50% confidenceFactExact time
To connect a private model through Private Inference, you need to add a base URL, choose an API format and add credentials, then register the models served by that endpoint.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/16/2026
First Seen
Valid until: 2/14/2027
Sources
Related Entities
Related Claims
UnverifiedWhen calling a private model, use a model ID in the form `private/<slug>`; AI Gateway translates the request into the format the endpoint requires, and switching between private and catalog models requires only changing the model ID.68% similarUnverifiedTo integrate a model in Dify, the model must first be configured under 'Model Providers'; models exist in plugin form and can be deployed locally or connected via an online model API Key.66% similarUnverifiedSelf-selected models are usually implemented through a unified model invocation interface that abstracts different vendors' APIs or local inference services into a single request format, so users can switch simply by changing the model identifier and key in the configuration.66% similarUnverifiedOpen weights mean the model parameters can be downloaded, inspected, modified and redistributed, whereas a closed-source API exposes only an inference interface.65% similarUnverifiedOpen-weight models let users download the parameters, run them on their own servers, fine-tune them and redistribute them; hosted services provide only an API, and users cannot access the model itself.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1177522API
curl https://kongchang.com/api/v1/knowledge/claims/1177522MCP
get_claim(id=1177522)