NVIDIA offers NIM
Service
Containerized inference microservices providing prebuilt APIs for popular AI models on NVIDIA accelerated infrastructure.
- Currently Offered
NVIDIA NIM is a catalog of containerized inference microservices that package optimized foundation models, retrieval models, vision models, and biology models behind standard REST APIs. Each microservice ships with the model, TensorRT and Triton-based runtime, and tuned configurations for NVIDIA GPUs.
Developers consume NIM through the NVIDIA API catalog at build.nvidia.com or deploy the containers behind a firewall through NVIDIA AI Enterprise on Kubernetes. NIM Agent Blueprints and NeMo microservices extend NIM for agent, RAG, and customer service workloads.
Containerized inference microservices providing prebuilt APIs for popular AI models on NVIDIA accelerated infrastructure.
RunInfra Model APIs provide hosted open-model inference through compatible APIs for developers and agent teams.
Vultr Serverless Inference deploys and serves generative AI models for businesses through managed GPU infrastructure.
Replicate is a cloud API to run, fine-tune, and deploy open-source machine learning models with auto-scaling.
GMI Cloud Inference is a Model-as-a-Service platform serving hosted LLM, image, video, and audio models through one unified API.
Vast.ai Model Library offers one-click deployment templates for open-source models.
Managed supervised fine-tuning service for open-source models with on-demand and dedicated deployment options.
Managed service for fine-tuning open-source models on dedicated or shared GPU infrastructure for production use.
Async inference API for long-horizon AI agents, serving leading open-source models through OpenAI- and Anthropic-compatible endpoints.
Fastest cloud for training/inference of 1B-24T models with no sharding.
Hosted inference API for the ESM model families with credit-based metering and a developer console.
Microsoft's managed cloud platform for accessing, fine-tuning, and deploying foundation models from OpenAI, Anthropic, Meta, and partner providers.
RunInfra Model APIs provide hosted open-model inference through compatible APIs for developers and agent teams.
Vultr Serverless Inference deploys and serves generative AI models for businesses through managed GPU infrastructure.
Vast.ai Serverless runs autoscaling GPU inference endpoints on managed capacity.
Replicate is a cloud API to run, fine-tune, and deploy open-source machine learning models with auto-scaling.
GMI Cloud Inference is a Model-as-a-Service platform serving hosted LLM, image, video, and audio models through one unified API.
Vast.ai Model Library offers one-click deployment templates for open-source models.
Managed supervised fine-tuning service for open-source models with on-demand and dedicated deployment options.
Managed service for fine-tuning open-source models on dedicated or shared GPU infrastructure for production use.
Async inference API for long-horizon AI agents, serving leading open-source models through OpenAI- and Anthropic-compatible endpoints.
Fastest cloud for training/inference of 1B-24T models with no sharding.
Hosted inference API for the ESM model families with credit-based metering and a developer console.
A unified AI gateway and LLM router exposing one OpenAI-compatible endpoint across 600+ models.
Microsoft's managed cloud platform for accessing, fine-tuning, and deploying foundation models from OpenAI, Anthropic, Meta, and partner providers.
Vast.ai Clusters provides dedicated multi-node GPU clusters for training workloads.
