NVIDIA NIM · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for NVIDIA NIM Biology (BioNeMo) ASR Completions API

2 actions 2 updates phrasing extends openapi/nvidia-nim-completions-api-openapi.yml
Generated by API Evangelist Written by API Evangelist tooling for NVIDIA NIM's API. It is a proposal applied on top of the contract, not a document NVIDIA NIM publishes.
View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 2

$.info
$.paths['/v1/completions'].post

OpenAPI Overlay

Raw ↑ 
# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for NVIDIA NIM Biology (BioNeMo) ASR Completions API
  version: 1.0.0
extends: openapi/nvidia-nim-completions-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-10-01'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 1
- target: $.paths['/v1/completions'].post
  update:
    x-apievangelist-phrasing:
      intent: Complete a raw text prompt
      effect: write
      questions:
      - Can I send a plain prompt string, not chat messages, and get a raw text continuation back?
      - Is it possible to get token log probabilities or echo the prompt in a text completion?
      - What stop sequences and max token limits can I set on a raw prompt completion?
      instructions:
      - text: Continue the raw prompt {prompt} with the {model} model.
        slots:
          prompt: requestBody.prompt
          model: requestBody.model
      - text: Complete {prompt} on {model}, generating at most {max_tokens} tokens and stopping at {stop}.
        slots:
          prompt: requestBody.prompt
          model: requestBody.model
          max_tokens: requestBody.max_tokens
          stop: requestBody.stop
      - text: Generate {n} alternative text completions of {prompt} from {model}.
        slots:
          n: requestBody.n
          prompt: requestBody.prompt
          model: requestBody.model
      method: generated
      generated: '2026-10-01'