Using Phi-3 Mini 128K on NVIDIA NIM
Implementation guide · Phi-3 · Microsoft Research
Quick Start
- 1
- 2Use the NVIDIA NIM SDK or REST API to call
phi-3-mini-128k— see the documentation for request format. - 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 Phi-3 Mini 128K
Phi-3 Mini-128K-Instruct, developed by Microsoft, is a 3.8 billion-parameter large language model renowned for its lightweight, open-source architecture. Despite its modest size, it excels in reasoning tasks, particularly in math and logic, and showcases strong code generation capabilities. A standout feature is its remarkable ability to handle up to 128,000 tokens, allowing it to process extensive text documents and codebases efficiently. While it has limitations in factual knowledge and focuses primarily on English, it strikes a balance between performance and efficiency, making it ideal for resource-constrained environments. The model is available on platforms like Azure AI Studio and Hugging Face and benefits from training on high-quality synthetic and publicly available data, with fine-tuning to improve instruction adherence and safety.