LLM Reference

Llama 4 Maverick 17B Instruct FP8

Open Source

About

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

Capabilities

MultimodalFunction CallingTool UseJSON Mode

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
Microsoft FoundryServerlessProvisioned

Specifications

FamilyLlama 4
Released2026-03-01
Parameters17B
Context128K
ArchitectureMixture of Experts
Specializationgeneral