llmreference
NVIDIA NIM

Using Llama 2 70B Chat on NVIDIA NIM

Implementation guide · Llama 2 · AI at Meta

ProvisionedOpen Source

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call llama2-70b-chat — see the documentation for request format.
  3. 3
    You'll be billed $1.00/GPU·hr. See full pricing.

Code Examples

See NVIDIA NIM documentation for integration details.

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

TypeRate
GPU Hour Rate$1.00/GPU·hr
GPU Config4xH100

Capabilities

Structured Outputs

About Llama 2 70B Chat

Llama 2 70B Chat is a large-scale language model with 70 billion parameters, designed for conversational AI applications. Released on July 18, 2023, it's part of Meta's Llama 2 family, featuring advanced transformer architecture optimized through supervised fine-tuning and reinforcement learning with human feedback. The model excels in generating human-like responses, outperforming many open-source alternatives and rivaling closed-source models like ChatGPT. Trained on 2 trillion tokens from diverse public sources, it's suitable for commercial and research applications in English, particularly for assistant-like functionalities. The model is available on Hugging Face for further exploration and implementation .

Model Specs

Released2023-07-18
Parameters70B
Context4K
ArchitectureDecoder Only

Provider

NVIDIA NIM
NVIDIA NIM

NVIDIA

Santa Clara, California, United States