All Models

Llama 4 Maverick

llama Tool Calling Attachments Open Weights 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 4
Released Apr 5, 2025
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Benchmarks

14.5
Intelligence Index
16.3
Coding Index
19.3
Math Index

Available Providers (4)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NanoGPT meta-llama/llama-4-maverick $0.15/MTok $0.60/MTok 1.0M 65.5K
OpenRouter meta-llama/llama-4-maverick $0.20/MTok $0.80/MTok 1.0M 16.4K
DigitalOcean llama-4-maverick $0.20/MTok $0.70/MTok 128K 16.4K
Kilo Gateway meta-llama/llama-4-maverick $0.20/MTok $0.70/MTok 1.0M 16.4K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output