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 Breeze 7B
Breeze-7B is an open-source large language model from MediaTek Research, engineered upon the Mistral-7B architecture. It excels in processing Traditional Chinese while also offering strong performance in English. Its 62,000-token vocabulary enhances comprehension and generation capabilities in Traditional Chinese, resulting in roughly twice the inference speed compared to similar models like Mistral-7B and Llama 7B. Breeze-7B includes multiple variants, such as a base model and instruction-tuned versions for tasks like question answering and summarization. Although a variant with a 64k-token context length was created, it was later removed due to performance issues. The model is competitive in benchmarks, notably those emphasizing Traditional Chinese.