Llama 4 Maverick
Meta Llama
· llama-4-maverick
Text and Language
Production
Lowest Cost
Open-weight workhorse with strong quality-per-dollar, deployable on any inference provider.
Best use cases: Social copy, drafts, high-volume generation
8
Quality
8
Speed
9.5
Cost Eff.
7.5
Brand Safety
7
Control
8
Adherence
Input cost
$0.22 / 1M tokens
Output cost
$0.85 / 1M tokens
Generation cost
—
Max context / duration
1M tokens
Aspect ratios
—
Resolutions
—
Input types
Text, images
Output types
Text
API endpoint
via OpenRouter / Together AI
Commercial use
Allowed
Data retention
Provider-dependent
Regions available
Global
API connected
Connected
Last updated
Release date
Documentation