Llama 4 Maverick 17B Instruct FP8 on Microsoft Foundry

Llama 4 · AI at Meta

ServerlessProvisioned
Open Weights

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

Why use Llama 4 Maverick 17B Instruct FP8 on Microsoft Foundry?

Microsoft Foundry offers Llama 4 Maverick 17B Instruct FP8 with pay-as-you-go pricing at $0.35/1M input tokens. Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development.

Compare Llama 4 Maverick 17B Instruct FP8 across 11 providers to find the best fit for your use case
Input / 1M
$0.35
Output / 1M
$1.41
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: Llama-4-Maverick-17B-128E-Instruct-FP8
Model ID
Llama-4-Maverick-17B-128E-Instruct-FP8

Request example

Curated snippets for this provider are not sourced yet. Use Microsoft Foundry documentation with model ID Llama-4-Maverick-17B-128E-Instruct-FP8.

Gotchas

  • Use provider model ID "Llama-4-Maverick-17B-128E-Instruct-FP8", not the LLMReference slug "llama-4-maverick-17b-128e-instruct-fp8".

Compare Llama 4 Maverick 17B Instruct FP8 Across Providers

ProviderInput (per 1M)Output (per 1M)
Microsoft Foundry$0.35$1.41
Together AI$0.27$0.85
OpenRouter$0.15$0.60
Fireworks AI——
DeepInfra$0.15$0.60
View all 11 providers →

Pricing

TypePrice (per 1M)
Input tokens$0.35
Output tokens$1.41

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.

Get Started

Model Specs

Released2025-04-05
Parameters400B (17B active)
Context1M
ArchitectureMixture of Experts
Knowledge cutoff2024-08

Related Models on Microsoft Foundry