Unverified50% confidenceFactExact time
When 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.
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 using Vercel AI Gateway, developers need only hold a single gateway key and make requests with model IDs in the form `<provider>/<model>`, rather than maintaining separate SDKs and account systems for each vendor.69% 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.69% similarUnverifiedTo 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.68% similarUnverifiedA custom iProvider allows users to enter their own API address, key and model name, thereby accessing models not built into the platform.68% similarVerifiedOpen-source models generally refer to AI models whose model weights can be publicly downloaded and which allow free use and modification, as opposed to closed-source models that are only accessible via API.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1177524API
curl https://kongchang.com/api/v1/knowledge/claims/1177524MCP
get_claim(id=1177524)