EN Submit a tool

meta-llama/llama-4-maverick-17b-128e-instruct

Rank #142 meta-llama

meta-llama/llama-4-maverick-17b-128e-instruct

Usage data date 2026-09-12 · updated daily

Usage and specs

Daily rank#142
Daily tokens16.5B
Daily requests7.9M
Daily change −16.1%
Released

What is meta-llama/llama-4-maverick-17b-128e-instruct

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...

meta-llama/llama-4-maverick-17b-128e-instruct capabilities

Input: Text、Image   Output: Text

JSON output Structured outputs Tool choice Tool use Knowledge cutoff 2024-08-31

meta-llama/llama-4-maverick-17b-128e-instruct API pricing

Input · per 1M tokens$0.20
Output · per 1M tokens$0.70

USD list-price snapshot, not independently verified; confirm current pricing and terms on the provider site before purchase.

Tools built on this model