NVIDIA NIM

NVIDIA NIM (NVIDIA Inference Microservices) is a catalog of GPU-accelerated, containerized AI inference microservices that package optimized model engines (TensorRT-LLM, vLLM, SGLang, Triton) behind industry-standard OpenAI-compatible REST APIs. NIM covers large language models, embeddings and reranking, vision-language models, speech (Riva), visual generative AI, and biology (BioNeMo) — exposed identically whether consumed from the hosted endpoint at integrate.api.nvidia.com or self-hosted via Docker containers and the Kubernetes-native NIM Operator. NIM ships with NVIDIA AI Enterprise for commercial deployment and is the inference layer underneath NVIDIA AI Blueprints, NeMo Retriever, NeMo Guardrails, and the broader NVIDIA developer stack.

10 APIs 19 Features

AIArtificial IntelligenceInferenceMicroservicesLLMFoundation ModelsGPUKubernetesNVIDIAOpenAI Compatible

APIs

NVIDIA NIM Chat Completions API

OpenAI-compatible chat completions endpoint exposing 100+ foundation models — Meta Llama, Mistral, Mixtral, NVIDIA Nemotron, DeepSeek, Qwen, Microsoft Phi, Google Gemma, IBM Gra...

NVIDIA NIM Completions API

Legacy OpenAI-compatible text completion endpoint (/v1/completions) for non-chat foundation models served by NIM. Accepts a raw prompt and returns generated text with the same s...

NVIDIA NIM Embeddings API

OpenAI-compatible embeddings endpoint (/v1/embeddings) backed by NVIDIA NeMo Retriever text embedding models including NV-Embed, NV-EmbedQA-E5, llama-3.2-nv-embedqa-1b, and BAAI...

NVIDIA NIM Reranking API

NeMo Retriever cross-encoder reranking endpoint (/v1/ranking) for scoring candidate passages against a query. Improves retrieval relevance on RAG pipelines and supports the llam...

NVIDIA NIM Models API

OpenAI-compatible model catalog endpoint (/v1/models) returning the list of models served by the NIM endpoint or container. Each entry includes id, owned_by, and created timesta...

NVIDIA NIM Vision Language Models API

Vision-language model inference through the standard /v1/chat/completions surface with image inputs (base64 or URL) in the messages payload. Supports NVIDIA NeVA, microsoft/kosm...

NVIDIA NIM Health API

Liveness, readiness, and startup probes exposed by self-hosted NIM containers (/v1/health/live, /v1/health/ready) and a Prometheus /v1/metrics scrape endpoint for GPU utilizatio...

NVIDIA NIM Image Generation API

Visual generative AI endpoints for text-to-image, image-to-image, and image editing using models such as Black Forest Labs FLUX.1, Stable Diffusion XL, Shutterstock-trained mode...

NVIDIA NIM Speech API

NVIDIA Riva-powered speech NIMs delivering automatic speech recognition (Parakeet, Canary), neural machine translation, and text-to-speech (Magpie-TTS, FastPitch) through HTTP a...

NVIDIA NIM Biology (BioNeMo) API

BioNeMo NIMs for protein structure prediction (AlphaFold2, ESMFold, OpenFold), protein generation (ProtGPT2, RFDiffusion), molecular property prediction (MolMIM), small molecule...

Agent Skills showing 24 of 237

PLANS

Rate Limits

Nvidia Nim Rate Limits

0 limits

RATE LIMITS

FinOps

Nvidia Nim Finops

FINOPS

Features

OpenAI-compatible REST surface — /v1/chat/completions, /v1/completions, /v1/embeddings, /v1/models, /v1/ranking

100+ foundation models exposed through a single API contract — Llama 3.1/3.2/3.3, Mistral, Mixtral, NVIDIA Nemotron, DeepSeek-R1, Qwen 2.5, Microsoft Phi, Google Gemma, IBM Granite, and Falcon

Free hosted inference at build.nvidia.com on DGX Cloud — 1,000 credits on signup, 40 RPM rate limit

Self-hosted deployment via Docker containers shipping TensorRT-LLM, vLLM, or SGLang inference engines

Kubernetes-native deployment via the NIM Operator with NIMService, NIMCache, NIMPipeline CRDs

GPU-aware autoscaling, persistent model caches, and rolling upgrades managed by the operator

Multi-tenant licensing through NVIDIA AI Enterprise (commercial production use)

NeMo Retriever NIMs for embeddings, reranking, OCR, and PDF-to-Markdown extraction in RAG pipelines

Vision Language Model NIMs reusing the chat-completions surface for multimodal inputs

NVIDIA Riva speech NIMs (Parakeet ASR, Canary translation, Magpie TTS) with HTTP and gRPC adapters

BioNeMo NIMs for AlphaFold2, ESMFold, ProtGPT2, MolMIM, DiffDock, RFDiffusion

Visual generative AI NIMs — FLUX.1, SDXL, Shutterstock Edify Image, Edify 3D

NeMo Guardrails for input/output safety and topic policy enforcement

Function calling, JSON mode, tool use, and structured outputs across compatible LLMs

Streaming via Server-Sent Events on chat/completions

Prometheus /v1/metrics scrape endpoint and /v1/health/{live,ready} probes for Kubernetes

LangChain, LlamaIndex, Haystack, OpenAI SDK, and direct REST client compatibility

NVIDIA AI Blueprints — full reference RAG, multimodal search, drug discovery, and digital human stacks

Available on DGX Cloud, AWS, Azure, Google Cloud, Oracle Cloud, GKE, EKS, AKS, OpenShift, and on-prem

GitHubOrganization

GitHubOrganization

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: NVIDIA NIM Vision Language Models API
  version: '2026-05-25'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Vision
    type: folder
  items:
  - info:
      name: Create A Multimodal Chat Completion
      type: http
    http:
      method: POST
      url: https://integrate.api.nvidia.com/v1/chat/completions
      body:
        type: json
        data: '{}'
    docs: 'Generate a chat completion against a vision-language model. Image content is supplied via `image_url` parts inside
      the user message; the response mirrors the standard chat completions schema.

      '
bundled: true