Llama 4 Maverick

Meta (via Together AI)

17B active parameter MoE model with 128 experts beating GPT-4o across broad benchmarks

Pricing

per 1M tokens

Input / 1M$0.27
Output / 1M$0.85

Specifications

API Model IDmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Context Window1M tokens
Max Output32K tokens

Modalities

textimage

Capabilities

tool-usestreamingjson-modevisioncode

Other Meta (via Together AI) Text / Chat Models

ModelInput / 1MOutput / 1MCache Read / 1MCache Write / 1M
Llama 4 Scout$0.18$0.59
Llama 3.3 70B$0.88$0.88