Using Llama 4 Maverick 17B Instruct FP8 on OpenRouter
Implementation guide · Llama 4 · AI at Meta
ServerlessOpen Source
Quick Start
- 1
- 2Use the OpenRouter SDK or REST API to call
meta-llama/llama-4-maverick— see the documentation for request format. - 3
Code Examples
About OpenRouter
OpenRouter provides a unified interface for Large Language Models with better pricing, improved uptime, and no subscription requirements. Route across providers for cost optimization and reliability.
OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.
Pricing on OpenRouter
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.15 |
| Output tokens | $0.60 |
Capabilities
Structured 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.
Model Specs
Released2025-04-05
Parameters17B
Context1M
ArchitectureMixture of Experts
Knowledge cutoff2024-08