Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.27 |
| Output tokens | $0.85 |
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.
Model Specs
Released2025-04-05
Parameters17B
Context1M
ArchitectureMixture of Experts