Using Llama 4 Maverick 17B Instruct FP8 on NVIDIA NIM

Implementation guide · Llama 4 · AI at Meta

ServerlessOpen Weights

NVIDIA NIM exposes Llama 4 Maverick 17B Instruct FP8 through model ID meta/llama-4-maverick-17b-128e-instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-09. Next refresh: weekly.

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 meta/llama-4-maverick-17b-128e-instruct — see the documentation for request format.
  3. 3
    You'll be billed . See full pricing.
API PortalDocumentationPricing

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

Capabilities

VisionMultimodalStructured Outputs

About Llama 4 Maverick 17B Instruct FP8

Meta's Llama 4 Maverick 17B with 128 experts, FP8-optimized for cost-efficient inference. Supports native Model Router integration on Microsoft Foundry.

Full model details →

Model Specs

Released2025-04-05
Parameters400B (17B active)
Context1m
ArchitectureMixture of Experts
Knowledge cutoff2024-08

More Models on NVIDIA NIM

Llama 4 Scout 17B-16E Instruct
All models on NVIDIA NIM →

Also available on(10)

OpenRouter$0.15/1MDeepInfra$0.15/1MAWS Bedrock$0.24/1M
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States