Quick Start
- 1
- 2
- 3
Code Examples
About NVIDIA NIM
NIM packages inference runtimes and model profiles into containers that expose standard API surfaces such as chat completions, completions, model listing, tokenization, health, and management endpoints. The hosted API path is useful for prototyping and catalog discovery, while the NGC/container path is the self-hosted route for teams that want GPU-hour infrastructure control, private-network deployment, Kubernetes scaling, or NVIDIA AI Enterprise support. Per-token pricing is not a universal provider-level claim in the current seed data; pricing should stay attached to sourced model-provider rows or NVIDIA's current catalog terms.
NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices. Developers can try hosted NIM APIs through the NVIDIA API Catalog on build.nvidia.com, then move the same model families into self-hosted NIM containers on NVIDIA GPUs in a data center, private cloud, public cloud, or workstation. The catalog positions NIM around optimized open and NVIDIA models, including chat, coding, reasoning, retrieval, vision, speech, and safety use cases, with downloadable model cards and API endpoints where NVIDIA exposes them.
Pricing on NVIDIA NIM
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
No model capability flags are currently sourced.
About NeVA 22B
NeVA-22B is a sophisticated vision-language model from NVIDIA, capable of interpreting and responding to intricate instructions that involve both text and images. It integrates a GPT-based language model with a CLIP model for image encoding, projecting image data into a shared text space for seamless processing. Trained with extensive datasets, including image-caption pairs and synthetic GPT-4 generated data, NeVA-22B excels in tasks such as language generation and visual question answering. It is optimized for NVIDIA’s hardware and utilizes Triton and TensorRT-LLM for efficient inference. Despite its advancements, users should be cautious of potential biases and inaccuracies in its outputs.