Models / Meta

Llama 4 Maverick (17B-128E Instruct)

GA

Open-weight, natively multimodal MoE: 17B active / 400B total params, 128 experts. License: Llama 4 Community License Agreement (commercial use permitted for orgs with <700M MAU). Meta is the model owner; no first-party Meta API pricing for self-host. Official Llama API model ID is 'Llama-4-Maverick-17B-128E-Instruct-FP8' and the Llama API serves it at a 128k context window (developer.meta.com/Llama API docs), whereas the open weights support up to 1M tokens. Hosted price shown is OpenRouter slug 'meta-llama/llama-4-maverick' = $0.15 in / $0.60 out per 1M (OpenRouter page accessed 2026-06-28).

Provider
Meta
Status
GA
Input price
$0.15 / 1M tokens
Output price
$0.6 / 1M tokens
Cached input
Blended price
$0.262 / 1M tokens
Context window
1,000,000 tokens (1M)
Max output
Modality
text, image
Knowledge cutoff
2024-08
Released
5 Apr 2025
API string
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

Source: Meta official documentation ↗