LLM Reference

Llama 4 Maverick 17B Instruct FP8 on OpenRouter

Llama 4 · AI at Meta

ServerlessOpen Source

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

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

DocsPortalPricing

Model Specs

Released2025-04-05
Parameters17B
Context1M
ArchitectureMixture of Experts

Other Providers(6)

Microsoft FoundryTogether AI$0.27/1MFireworks AIDeepInfraGCP Vertex AI$0.35/1MNVIDIA NIM$0/1M
Compare all providers →

Related Models on OpenRouter

Llama 4 Scout 17B-16E Instruct

Provider

OpenRouter

OpenRouter, Inc.

All models on OpenRouter →