Sign in
NVIDIA NIM Pass-through
pass-through

Nvidia Nim Proxy Route

Relay a native NVIDIA NIM request through a LiteLLM model group.

{PROXY_BASE_URL}/nvidia_nim/{model_group}/v1/infer forwards the body unchanged to the deployment's api_base, so object detection and OCR NIMs whose payload carries no model field still go through virtual key auth, model access checks, and spend logging.

delete/nvidia_nim/{endpoint}

Path parameters

endpointstring required

Response

Successful Response

{"stackTrail":"paths:/nvidia_nim/{endpoint}:delete:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}

Changes

Changed in 4 of the 51 revisions of this API.10

  • 611a0ed75fe83See the full diff
    • ○

      api tag NVIDIA NIM Pass-through added

      api-tag-added

    • ○

      api tag pass-through added

      api-tag-added

    • ○

      api tag llm_passthrough removed

      api-tag-removed

  • 51c2ca10dc0b3See the full diff
    • ○

      api tag llm_passthrough added

      api-tag-added

    • ○

      api tag NVIDIA NIM Pass-through removed

      api-tag-removed

    • ○

      api tag pass-through removed

      api-tag-removed

  • c94c9b11f95e3See the full diff
    • ○

      api tag NVIDIA NIM Pass-through added

      api-tag-added

    • ○

      api tag pass-through added

      api-tag-added

    • ○

      api tag llm_passthrough removed

      api-tag-removed

  • 85ac4287140e1See the full diff
    • ○

      endpoint added

      endpoint-added