Nexus

NVIDIA NIM

Use NVIDIA NIM for GPU-optimized inference and embeddings with Nexus.

NVIDIA NIM provides GPU-optimized inference with embedding support. Uses an OpenAI-compatible API.

Installation

import "github.com/xraph/nexus/providers/nvidia"

Quick Start

provider := nvidia.New(os.Getenv("NVIDIA_API_KEY"))

gw := nexus.New(
    nexus.WithProvider(provider),
)

Options

OptionDescription
nvidia.WithBaseURL(url)Override the API base URL (default: https://integrate.api.nvidia.com/v1)

Capabilities

CapabilitySupported
ChatYes
StreamingYes
EmbeddingsYes
VisionNo
ToolsYes
ThinkingNo

Models

ModelContextMax OutputInput PriceOutput Price
meta/llama-3.1-405b-instruct131K4,096$5.00/M$16.00/M
meta/llama-3.1-8b-instruct131K4,096$0.30/M$0.50/M
nvidia/nv-embedqa-e5-v5512$0.02/M

On this page