Proxy service for NIM microservices
End of Support — "This artifact is no longer supported. NVIDIA strongly recommends artifacts that are up to date and supported"
NeMo NIM Proxy Microservice Container
NeMo NIM Proxy microservice provides a unified access point for all NVIDIA NIM (NVIDIA Inference Microservice) deployments within your Kubernetes cluster through a single OpenAI-compatible API.
You can use the NIM Proxy to interact with multiple deployed models through standardized endpoints for retrieving model lists and making inference requests to chat completions and completions APIs.
Note: NeMo microservices has been sunset as of October 1, 2026. There will be no new releases.
Resources
Note: Use, distribution or deployment of this microservice in production requires an NVIDIA AI Enterprise License.
Governing Terms
The software and materials are governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.
Get Help
NVIDIA Developer Community Forum
For support, Visit the NVIDIA Developer Community Forum