All Models

Llama 4 Maverick

llama Tool Calling Attachments Structured Output

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Providers 1
Released Sep 5, 2025
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Benchmarks

18.4
Intelligence Index
15.6
Coding Index
19.3
Math Index

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NanoGPT meta-llama/llama-4-maverick $0.18/MTok $0.80/MTok 1.0M 65.5K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output